diff --git a/[refs] b/[refs]
index a732b5c530c2..398e83a5f9eb 100644
--- a/[refs]
+++ b/[refs]
@@ -1,2 +1,2 @@
---
-refs/heads/master: 2419505acc479d2f1feed94d195b0554a64269a4
+refs/heads/master: 6bd8fedaa16da1e24f38712ee759950d8c5f4f09
diff --git a/trunk/Documentation/DocBook/kernel-api.tmpl b/trunk/Documentation/DocBook/kernel-api.tmpl
index 77436d735013..aa38cc5692a0 100644
--- a/trunk/Documentation/DocBook/kernel-api.tmpl
+++ b/trunk/Documentation/DocBook/kernel-api.tmpl
@@ -419,13 +419,7 @@ X!Edrivers/pnp/system.c
Block Devices
-!Eblock/blk-core.c
-!Eblock/blk-map.c
-!Iblock/blk-sysfs.c
-!Eblock/blk-settings.c
-!Eblock/blk-exec.c
-!Eblock/blk-barrier.c
-!Eblock/blk-tag.c
+!Eblock/ll_rw_blk.c
diff --git a/trunk/Documentation/debugging-via-ohci1394.txt b/trunk/Documentation/debugging-via-ohci1394.txt
deleted file mode 100644
index de4804e8b396..000000000000
--- a/trunk/Documentation/debugging-via-ohci1394.txt
+++ /dev/null
@@ -1,179 +0,0 @@
-
- Using physical DMA provided by OHCI-1394 FireWire controllers for debugging
- ---------------------------------------------------------------------------
-
-Introduction
-------------
-
-Basically all FireWire controllers which are in use today are compliant
-to the OHCI-1394 specification which defines the controller to be a PCI
-bus master which uses DMA to offload data transfers from the CPU and has
-a "Physical Response Unit" which executes specific requests by employing
-PCI-Bus master DMA after applying filters defined by the OHCI-1394 driver.
-
-Once properly configured, remote machines can send these requests to
-ask the OHCI-1394 controller to perform read and write requests on
-physical system memory and, for read requests, send the result of
-the physical memory read back to the requester.
-
-With that, it is possible to debug issues by reading interesting memory
-locations such as buffers like the printk buffer or the process table.
-
-Retrieving a full system memory dump is also possible over the FireWire,
-using data transfer rates in the order of 10MB/s or more.
-
-Memory access is currently limited to the low 4G of physical address
-space which can be a problem on IA64 machines where memory is located
-mostly above that limit, but it is rarely a problem on more common
-hardware such as hardware based on x86, x86-64 and PowerPC.
-
-Together with a early initialization of the OHCI-1394 controller for debugging,
-this facility proved most useful for examining long debugs logs in the printk
-buffer on to debug early boot problems in areas like ACPI where the system
-fails to boot and other means for debugging (serial port) are either not
-available (notebooks) or too slow for extensive debug information (like ACPI).
-
-Drivers
--------
-
-The OHCI-1394 drivers in drivers/firewire and drivers/ieee1394 initialize
-the OHCI-1394 controllers to a working state and can be used to enable
-physical DMA. By default you only have to load the driver, and physical
-DMA access will be granted to all remote nodes, but it can be turned off
-when using the ohci1394 driver.
-
-Because these drivers depend on the PCI enumeration to be completed, an
-initialization routine which can runs pretty early (long before console_init(),
-which makes the printk buffer appear on the console can be called) was written.
-
-To activate it, enable CONFIG_PROVIDE_OHCI1394_DMA_INIT (Kernel hacking menu:
-Provide code for enabling DMA over FireWire early on boot) and pass the
-parameter "ohci1394_dma=early" to the recompiled kernel on boot.
-
-Tools
------
-
-firescope - Originally developed by Benjamin Herrenschmidt, Andi Kleen ported
-it from PowerPC to x86 and x86_64 and added functionality, firescope can now
-be used to view the printk buffer of a remote machine, even with live update.
-
-Bernhard Kaindl enhanced firescope to support accessing 64-bit machines
-from 32-bit firescope and vice versa:
-- ftp://ftp.suse.de/private/bk/firewire/tools/firescope-0.2.2.tar.bz2
-
-and he implemented fast system dump (alpha version - read README.txt):
-- ftp://ftp.suse.de/private/bk/firewire/tools/firedump-0.1.tar.bz2
-
-There is also a gdb proxy for firewire which allows to use gdb to access
-data which can be referenced from symbols found by gdb in vmlinux:
-- ftp://ftp.suse.de/private/bk/firewire/tools/fireproxy-0.33.tar.bz2
-
-The latest version of this gdb proxy (fireproxy-0.34) can communicate (not
-yet stable) with kgdb over an memory-based communication module (kgdbom).
-
-Getting Started
----------------
-
-The OHCI-1394 specification regulates that the OHCI-1394 controller must
-disable all physical DMA on each bus reset.
-
-This means that if you want to debug an issue in a system state where
-interrupts are disabled and where no polling of the OHCI-1394 controller
-for bus resets takes place, you have to establish any FireWire cable
-connections and fully initialize all FireWire hardware __before__ the
-system enters such state.
-
-Step-by-step instructions for using firescope with early OHCI initialization:
-
-1) Verify that your hardware is supported:
-
- Load the ohci1394 or the fw-ohci module and check your kernel logs.
- You should see a line similar to
-
- ohci1394: fw-host0: OHCI-1394 1.1 (PCI): IRQ=[18] MMIO=[fe9ff800-fe9fffff]
- ... Max Packet=[2048] IR/IT contexts=[4/8]
-
- when loading the driver. If you have no supported controller, many PCI,
- CardBus and even some Express cards which are fully compliant to OHCI-1394
- specification are available. If it requires no driver for Windows operating
- systems, it most likely is. Only specialized shops have cards which are not
- compliant, they are based on TI PCILynx chips and require drivers for Win-
- dows operating systems.
-
-2) Establish a working FireWire cable connection:
-
- Any FireWire cable, as long at it provides electrically and mechanically
- stable connection and has matching connectors (there are small 4-pin and
- large 6-pin FireWire ports) will do.
-
- If an driver is running on both machines you should see a line like
-
- ieee1394: Node added: ID:BUS[0-01:1023] GUID[0090270001b84bba]
-
- on both machines in the kernel log when the cable is plugged in
- and connects the two machines.
-
-3) Test physical DMA using firescope:
-
- On the debug host,
- - load the raw1394 module,
- - make sure that /dev/raw1394 is accessible,
- then start firescope:
-
- $ firescope
- Port 0 (ohci1394) opened, 2 nodes detected
-
- FireScope
- ---------
- Target :
- Gen : 1
- [Ctrl-T] choose target
- [Ctrl-H] this menu
- [Ctrl-Q] quit
-
- ------> Press Ctrl-T now, the output should be similar to:
-
- 2 nodes available, local node is: 0
- 0: ffc0, uuid: 00000000 00000000 [LOCAL]
- 1: ffc1, uuid: 00279000 ba4bb801
-
- Besides the [LOCAL] node, it must show another node without error message.
-
-4) Prepare for debugging with early OHCI-1394 initialization:
-
- 4.1) Kernel compilation and installation on debug target
-
- Compile the kernel to be debugged with CONFIG_PROVIDE_OHCI1394_DMA_INIT
- (Kernel hacking: Provide code for enabling DMA over FireWire early on boot)
- enabled and install it on the machine to be debugged (debug target).
-
- 4.2) Transfer the System.map of the debugged kernel to the debug host
-
- Copy the System.map of the kernel be debugged to the debug host (the host
- which is connected to the debugged machine over the FireWire cable).
-
-5) Retrieving the printk buffer contents:
-
- With the FireWire cable connected, the OHCI-1394 driver on the debugging
- host loaded, reboot the debugged machine, booting the kernel which has
- CONFIG_PROVIDE_OHCI1394_DMA_INIT enabled, with the option ohci1394_dma=early.
-
- Then, on the debugging host, run firescope, for example by using -A:
-
- firescope -A System.map-of-debug-target-kernel
-
- Note: -A automatically attaches to the first non-local node. It only works
- reliably if only connected two machines are connected using FireWire.
-
- After having attached to the debug target, press Ctrl-D to view the
- complete printk buffer or Ctrl-U to enter auto update mode and get an
- updated live view of recent kernel messages logged on the debug target.
-
- Call "firescope -h" to get more information on firescope's options.
-
-Notes
------
-Documentation and specifications: ftp://ftp.suse.de/private/bk/firewire/docs
-
-FireWire is a trademark of Apple Inc. - for more information please refer to:
-http://en.wikipedia.org/wiki/FireWire
diff --git a/trunk/Documentation/kernel-parameters.txt b/trunk/Documentation/kernel-parameters.txt
index 5d171b7b8393..880f882160e2 100644
--- a/trunk/Documentation/kernel-parameters.txt
+++ b/trunk/Documentation/kernel-parameters.txt
@@ -416,21 +416,8 @@ and is between 256 and 4096 characters. It is defined in the file
[SPARC64] tick
[X86-64] hpet,tsc
- clearcpuid=BITNUM [X86]
- Disable CPUID feature X for the kernel. See
- include/asm-x86/cpufeature.h for the valid bit numbers.
- Note the Linux specific bits are not necessarily
- stable over kernel options, but the vendor specific
- ones should be.
- Also note that user programs calling CPUID directly
- or using the feature without checking anything
- will still see it. This just prevents it from
- being used by the kernel or shown in /proc/cpuinfo.
- Also note the kernel might malfunction if you disable
- some critical bits.
-
- code_bytes [IA32/X86_64] How many bytes of object code to print
- in an oops report.
+ code_bytes [IA32] How many bytes of object code to print in an
+ oops report.
Range: 0 - 8192
Default: 64
@@ -583,12 +570,6 @@ and is between 256 and 4096 characters. It is defined in the file
See drivers/char/README.epca and
Documentation/digiepca.txt.
- disable_mtrr_trim [X86, Intel and AMD only]
- By default the kernel will trim any uncacheable
- memory out of your available memory pool based on
- MTRR settings. This parameter disables that behavior,
- possibly causing your machine to run very slowly.
-
dmasound= [HW,OSS] Sound subsystem buffers
dscc4.setup= [NET]
@@ -679,10 +660,6 @@ and is between 256 and 4096 characters. It is defined in the file
gamma= [HW,DRM]
- gart_fix_e820= [X86_64] disable the fix e820 for K8 GART
- Format: off | on
- default: on
-
gdth= [HW,SCSI]
See header of drivers/scsi/gdth.c.
@@ -817,16 +794,6 @@ and is between 256 and 4096 characters. It is defined in the file
for translation below 32 bit and if not available
then look in the higher range.
- io_delay= [X86-32,X86-64] I/O delay method
- 0x80
- Standard port 0x80 based delay
- 0xed
- Alternate port 0xed based delay (needed on some systems)
- udelay
- Simple two microseconds delay
- none
- No delay
-
io7= [HW] IO7 for Marvel based alpha systems
See comment before marvel_specify_io7 in
arch/alpha/kernel/core_marvel.c.
@@ -1092,11 +1059,6 @@ and is between 256 and 4096 characters. It is defined in the file
Multi-Function General Purpose Timers on AMD Geode
platforms.
- mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
- the BIOS has incorrectly applied a workaround. TinyBIOS
- version 0.98 is known to be affected, 0.99 fixes the
- problem by letting the user disable the workaround.
-
mga= [HW,DRM]
mousedev.tap_time=
@@ -1197,8 +1159,6 @@ and is between 256 and 4096 characters. It is defined in the file
nodisconnect [HW,SCSI,M68K] Disables SCSI disconnects.
- noefi [X86-32,X86-64] Disable EFI runtime services support.
-
noexec [IA-64]
noexec [X86-32,X86-64]
@@ -1209,8 +1169,6 @@ and is between 256 and 4096 characters. It is defined in the file
register save and restore. The kernel will only save
legacy floating-point registers on task switch.
- noclflush [BUGS=X86] Don't use the CLFLUSH instruction
-
nohlt [BUGS=ARM]
no-hlt [BUGS=X86-32] Tells the kernel that the hlt
@@ -2020,11 +1978,6 @@ and is between 256 and 4096 characters. It is defined in the file
vdso=1: enable VDSO (default)
vdso=0: disable VDSO mapping
- vdso32= [X86-32,X86-64]
- vdso32=2: enable compat VDSO (default with COMPAT_VDSO)
- vdso32=1: enable 32-bit VDSO (default)
- vdso32=0: disable 32-bit VDSO mapping
-
vector= [IA-64,SMP]
vector=percpu: enable percpu vector domain
diff --git a/trunk/Documentation/x86_64/boot-options.txt b/trunk/Documentation/x86_64/boot-options.txt
index 34abae4e9442..945311840a10 100644
--- a/trunk/Documentation/x86_64/boot-options.txt
+++ b/trunk/Documentation/x86_64/boot-options.txt
@@ -110,18 +110,12 @@ Idle loop
Rebooting
- reboot=b[ios] | t[riple] | k[bd] | a[cpi] | e[fi] [, [w]arm | [c]old]
+ reboot=b[ios] | t[riple] | k[bd] [, [w]arm | [c]old]
bios Use the CPU reboot vector for warm reset
warm Don't set the cold reboot flag
cold Set the cold reboot flag
triple Force a triple fault (init)
kbd Use the keyboard controller. cold reset (default)
- acpi Use the ACPI RESET_REG in the FADT. If ACPI is not configured or the
- ACPI reset does not work, the reboot path attempts the reset using
- the keyboard controller.
- efi Use efi reset_system runtime service. If EFI is not configured or the
- EFI reset does not work, the reboot path attempts the reset using
- the keyboard controller.
Using warm reset will be much faster especially on big memory
systems because the BIOS will not go through the memory check.
diff --git a/trunk/Documentation/x86_64/uefi.txt b/trunk/Documentation/x86_64/uefi.txt
index 7d77120a5184..91a98edfb588 100644
--- a/trunk/Documentation/x86_64/uefi.txt
+++ b/trunk/Documentation/x86_64/uefi.txt
@@ -19,10 +19,6 @@ Mechanics:
- Build the kernel with the following configuration.
CONFIG_FB_EFI=y
CONFIG_FRAMEBUFFER_CONSOLE=y
- If EFI runtime services are expected, the following configuration should
- be selected.
- CONFIG_EFI=y
- CONFIG_EFI_VARS=y or m # optional
- Create a VFAT partition on the disk
- Copy the following to the VFAT partition:
elilo bootloader with x86_64 support, elilo configuration file,
@@ -31,8 +27,3 @@ Mechanics:
can be found in the elilo sourceforge project.
- Boot to EFI shell and invoke elilo choosing the kernel image built
in first step.
-- If some or all EFI runtime services don't work, you can try following
- kernel command line parameters to turn off some or all EFI runtime
- services.
- noefi turn off all EFI runtime services
- reboot_type=k turn off EFI reboot runtime service
diff --git a/trunk/arch/arm/Kconfig b/trunk/arch/arm/Kconfig
index 77201d3f7479..de211ac3853e 100644
--- a/trunk/arch/arm/Kconfig
+++ b/trunk/arch/arm/Kconfig
@@ -91,11 +91,6 @@ config GENERIC_IRQ_PROBE
bool
default y
-config GENERIC_LOCKBREAK
- bool
- default y
- depends on SMP && PREEMPT
-
config RWSEM_GENERIC_SPINLOCK
bool
default y
diff --git a/trunk/arch/ia64/Kconfig b/trunk/arch/ia64/Kconfig
index 5a41e75ae1fe..bef47725d4ad 100644
--- a/trunk/arch/ia64/Kconfig
+++ b/trunk/arch/ia64/Kconfig
@@ -42,11 +42,6 @@ config MMU
config SWIOTLB
bool
-config GENERIC_LOCKBREAK
- bool
- default y
- depends on SMP && PREEMPT
-
config RWSEM_XCHGADD_ALGORITHM
bool
default y
@@ -80,9 +75,6 @@ config GENERIC_TIME_VSYSCALL
bool
default y
-config ARCH_SETS_UP_PER_CPU_AREA
- def_bool y
-
config DMI
bool
default y
diff --git a/trunk/arch/ia64/hp/sim/simscsi.c b/trunk/arch/ia64/hp/sim/simscsi.c
index 7661bb065fa5..6ef9b5219930 100644
--- a/trunk/arch/ia64/hp/sim/simscsi.c
+++ b/trunk/arch/ia64/hp/sim/simscsi.c
@@ -360,6 +360,7 @@ static struct scsi_host_template driver_template = {
.max_sectors = 1024,
.cmd_per_lun = SIMSCSI_REQ_QUEUE_LEN,
.use_clustering = DISABLE_CLUSTERING,
+ .use_sg_chaining = ENABLE_SG_CHAINING,
};
static int __init
diff --git a/trunk/arch/ia64/ia32/binfmt_elf32.c b/trunk/arch/ia64/ia32/binfmt_elf32.c
index 4f0c30c38e99..3e35987af458 100644
--- a/trunk/arch/ia64/ia32/binfmt_elf32.c
+++ b/trunk/arch/ia64/ia32/binfmt_elf32.c
@@ -222,8 +222,7 @@ elf32_set_personality (void)
}
static unsigned long
-elf32_map(struct file *filep, unsigned long addr, struct elf_phdr *eppnt,
- int prot, int type, unsigned long unused)
+elf32_map (struct file *filep, unsigned long addr, struct elf_phdr *eppnt, int prot, int type)
{
unsigned long pgoff = (eppnt->p_vaddr) & ~IA32_PAGE_MASK;
diff --git a/trunk/arch/ia64/kernel/module.c b/trunk/arch/ia64/kernel/module.c
index e699eb6c44be..196287928bae 100644
--- a/trunk/arch/ia64/kernel/module.c
+++ b/trunk/arch/ia64/kernel/module.c
@@ -947,7 +947,7 @@ percpu_modcopy (void *pcpudst, const void *src, unsigned long size)
{
unsigned int i;
for_each_possible_cpu(i) {
- memcpy(pcpudst + per_cpu_offset(i), src, size);
+ memcpy(pcpudst + __per_cpu_offset[i], src, size);
}
}
#endif /* CONFIG_SMP */
diff --git a/trunk/arch/m32r/Kconfig b/trunk/arch/m32r/Kconfig
index f7237c5f531e..ab9a264cb194 100644
--- a/trunk/arch/m32r/Kconfig
+++ b/trunk/arch/m32r/Kconfig
@@ -235,11 +235,6 @@ config IRAM_SIZE
# Define implied options from the CPU selection here
#
-config GENERIC_LOCKBREAK
- bool
- default y
- depends on SMP && PREEMPT
-
config RWSEM_GENERIC_SPINLOCK
bool
depends on M32R
diff --git a/trunk/arch/mips/Kconfig b/trunk/arch/mips/Kconfig
index 4fad0a34b997..6b0f85f02c79 100644
--- a/trunk/arch/mips/Kconfig
+++ b/trunk/arch/mips/Kconfig
@@ -694,11 +694,6 @@ source "arch/mips/vr41xx/Kconfig"
endmenu
-config GENERIC_LOCKBREAK
- bool
- default y
- depends on SMP && PREEMPT
-
config RWSEM_GENERIC_SPINLOCK
bool
default y
diff --git a/trunk/arch/mips/kernel/i8253.c b/trunk/arch/mips/kernel/i8253.c
index fc4aa07b6d35..c2d497ceffdd 100644
--- a/trunk/arch/mips/kernel/i8253.c
+++ b/trunk/arch/mips/kernel/i8253.c
@@ -24,7 +24,9 @@ DEFINE_SPINLOCK(i8253_lock);
static void init_pit_timer(enum clock_event_mode mode,
struct clock_event_device *evt)
{
- spin_lock(&i8253_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&i8253_lock, flags);
switch(mode) {
case CLOCK_EVT_MODE_PERIODIC:
@@ -53,7 +55,7 @@ static void init_pit_timer(enum clock_event_mode mode,
/* Nothing to do here */
break;
}
- spin_unlock(&i8253_lock);
+ spin_unlock_irqrestore(&i8253_lock, flags);
}
/*
@@ -63,10 +65,12 @@ static void init_pit_timer(enum clock_event_mode mode,
*/
static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
{
- spin_lock(&i8253_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&i8253_lock, flags);
outb_p(delta & 0xff , PIT_CH0); /* LSB */
outb(delta >> 8 , PIT_CH0); /* MSB */
- spin_unlock(&i8253_lock);
+ spin_unlock_irqrestore(&i8253_lock, flags);
return 0;
}
diff --git a/trunk/arch/parisc/Kconfig b/trunk/arch/parisc/Kconfig
index 2b649c46631c..b8ef1787a191 100644
--- a/trunk/arch/parisc/Kconfig
+++ b/trunk/arch/parisc/Kconfig
@@ -19,11 +19,6 @@ config MMU
config STACK_GROWSUP
def_bool y
-config GENERIC_LOCKBREAK
- bool
- default y
- depends on SMP && PREEMPT
-
config RWSEM_GENERIC_SPINLOCK
def_bool y
diff --git a/trunk/arch/powerpc/Kconfig b/trunk/arch/powerpc/Kconfig
index fb85f6b72fcf..232c298c933f 100644
--- a/trunk/arch/powerpc/Kconfig
+++ b/trunk/arch/powerpc/Kconfig
@@ -42,9 +42,6 @@ config GENERIC_HARDIRQS
bool
default y
-config ARCH_SETS_UP_PER_CPU_AREA
- def_bool PPC64
-
config IRQ_PER_CPU
bool
default y
@@ -56,11 +53,6 @@ config RWSEM_XCHGADD_ALGORITHM
bool
default y
-config GENERIC_LOCKBREAK
- bool
- default y
- depends on SMP && PREEMPT
-
config ARCH_HAS_ILOG2_U32
bool
default y
diff --git a/trunk/arch/powerpc/kernel/ptrace.c b/trunk/arch/powerpc/kernel/ptrace.c
index 8b056d2295cc..3e17d154d0d4 100644
--- a/trunk/arch/powerpc/kernel/ptrace.c
+++ b/trunk/arch/powerpc/kernel/ptrace.c
@@ -256,7 +256,7 @@ static int set_evrregs(struct task_struct *task, unsigned long *data)
#endif /* CONFIG_SPE */
-void user_enable_single_step(struct task_struct *task)
+static void set_single_step(struct task_struct *task)
{
struct pt_regs *regs = task->thread.regs;
@@ -271,7 +271,7 @@ void user_enable_single_step(struct task_struct *task)
set_tsk_thread_flag(task, TIF_SINGLESTEP);
}
-void user_disable_single_step(struct task_struct *task)
+static void clear_single_step(struct task_struct *task)
{
struct pt_regs *regs = task->thread.regs;
@@ -313,7 +313,7 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
void ptrace_disable(struct task_struct *child)
{
/* make sure the single step bit is not set. */
- user_disable_single_step(child);
+ clear_single_step(child);
}
/*
@@ -445,6 +445,52 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
break;
}
+ case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
+ case PTRACE_CONT: { /* restart after signal. */
+ ret = -EIO;
+ if (!valid_signal(data))
+ break;
+ if (request == PTRACE_SYSCALL)
+ set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ else
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ child->exit_code = data;
+ /* make sure the single step bit is not set. */
+ clear_single_step(child);
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+/*
+ * make the child exit. Best I can do is send it a sigkill.
+ * perhaps it should be put in the status that it wants to
+ * exit.
+ */
+ case PTRACE_KILL: {
+ ret = 0;
+ if (child->exit_state == EXIT_ZOMBIE) /* already dead */
+ break;
+ child->exit_code = SIGKILL;
+ /* make sure the single step bit is not set. */
+ clear_single_step(child);
+ wake_up_process(child);
+ break;
+ }
+
+ case PTRACE_SINGLESTEP: { /* set the trap flag. */
+ ret = -EIO;
+ if (!valid_signal(data))
+ break;
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ set_single_step(child);
+ child->exit_code = data;
+ /* give it a chance to run. */
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
case PTRACE_GET_DEBUGREG: {
ret = -EINVAL;
/* We only support one DABR and no IABRS at the moment */
diff --git a/trunk/arch/sparc64/Kconfig b/trunk/arch/sparc64/Kconfig
index 26f5791baa33..10b212a1f9f5 100644
--- a/trunk/arch/sparc64/Kconfig
+++ b/trunk/arch/sparc64/Kconfig
@@ -66,9 +66,6 @@ config AUDIT_ARCH
bool
default y
-config ARCH_SETS_UP_PER_CPU_AREA
- def_bool y
-
config ARCH_NO_VIRT_TO_BUS
def_bool y
@@ -203,11 +200,6 @@ config US2E_FREQ
If in doubt, say N.
# Global things across all Sun machines.
-config GENERIC_LOCKBREAK
- bool
- default y
- depends on SMP && PREEMPT
-
config RWSEM_GENERIC_SPINLOCK
bool
diff --git a/trunk/arch/um/kernel/ksyms.c b/trunk/arch/um/kernel/ksyms.c
index 7c7142ba3bd7..1b388b41d95d 100644
--- a/trunk/arch/um/kernel/ksyms.c
+++ b/trunk/arch/um/kernel/ksyms.c
@@ -71,10 +71,10 @@ EXPORT_SYMBOL(dump_thread);
/* required for SMP */
-extern void __write_lock_failed(rwlock_t *rw);
+extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
EXPORT_SYMBOL(__write_lock_failed);
-extern void __read_lock_failed(rwlock_t *rw);
+extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
EXPORT_SYMBOL(__read_lock_failed);
#endif
diff --git a/trunk/arch/um/sys-i386/signal.c b/trunk/arch/um/sys-i386/signal.c
index 19053d46cb60..0147227ce18d 100644
--- a/trunk/arch/um/sys-i386/signal.c
+++ b/trunk/arch/um/sys-i386/signal.c
@@ -3,10 +3,10 @@
* Licensed under the GPL
*/
-#include
-#include
-#include
-#include
+#include "linux/ptrace.h"
+#include "asm/unistd.h"
+#include "asm/uaccess.h"
+#include "asm/ucontext.h"
#include "frame_kern.h"
#include "skas.h"
@@ -18,17 +18,17 @@ void copy_sc(struct uml_pt_regs *regs, void *from)
REGS_FS(regs->gp) = sc->fs;
REGS_ES(regs->gp) = sc->es;
REGS_DS(regs->gp) = sc->ds;
- REGS_EDI(regs->gp) = sc->di;
- REGS_ESI(regs->gp) = sc->si;
- REGS_EBP(regs->gp) = sc->bp;
- REGS_SP(regs->gp) = sc->sp;
- REGS_EBX(regs->gp) = sc->bx;
- REGS_EDX(regs->gp) = sc->dx;
- REGS_ECX(regs->gp) = sc->cx;
- REGS_EAX(regs->gp) = sc->ax;
- REGS_IP(regs->gp) = sc->ip;
+ REGS_EDI(regs->gp) = sc->edi;
+ REGS_ESI(regs->gp) = sc->esi;
+ REGS_EBP(regs->gp) = sc->ebp;
+ REGS_SP(regs->gp) = sc->esp;
+ REGS_EBX(regs->gp) = sc->ebx;
+ REGS_EDX(regs->gp) = sc->edx;
+ REGS_ECX(regs->gp) = sc->ecx;
+ REGS_EAX(regs->gp) = sc->eax;
+ REGS_IP(regs->gp) = sc->eip;
REGS_CS(regs->gp) = sc->cs;
- REGS_EFLAGS(regs->gp) = sc->flags;
+ REGS_EFLAGS(regs->gp) = sc->eflags;
REGS_SS(regs->gp) = sc->ss;
}
@@ -229,18 +229,18 @@ static int copy_sc_to_user(struct sigcontext __user *to,
sc.fs = REGS_FS(regs->regs.gp);
sc.es = REGS_ES(regs->regs.gp);
sc.ds = REGS_DS(regs->regs.gp);
- sc.di = REGS_EDI(regs->regs.gp);
- sc.si = REGS_ESI(regs->regs.gp);
- sc.bp = REGS_EBP(regs->regs.gp);
- sc.sp = sp;
- sc.bx = REGS_EBX(regs->regs.gp);
- sc.dx = REGS_EDX(regs->regs.gp);
- sc.cx = REGS_ECX(regs->regs.gp);
- sc.ax = REGS_EAX(regs->regs.gp);
- sc.ip = REGS_IP(regs->regs.gp);
+ sc.edi = REGS_EDI(regs->regs.gp);
+ sc.esi = REGS_ESI(regs->regs.gp);
+ sc.ebp = REGS_EBP(regs->regs.gp);
+ sc.esp = sp;
+ sc.ebx = REGS_EBX(regs->regs.gp);
+ sc.edx = REGS_EDX(regs->regs.gp);
+ sc.ecx = REGS_ECX(regs->regs.gp);
+ sc.eax = REGS_EAX(regs->regs.gp);
+ sc.eip = REGS_IP(regs->regs.gp);
sc.cs = REGS_CS(regs->regs.gp);
- sc.flags = REGS_EFLAGS(regs->regs.gp);
- sc.sp_at_signal = regs->regs.gp[UESP];
+ sc.eflags = REGS_EFLAGS(regs->regs.gp);
+ sc.esp_at_signal = regs->regs.gp[UESP];
sc.ss = regs->regs.gp[SS];
sc.cr2 = fi->cr2;
sc.err = fi->error_code;
diff --git a/trunk/arch/um/sys-x86_64/signal.c b/trunk/arch/um/sys-x86_64/signal.c
index 7457436b433a..1778d33808f4 100644
--- a/trunk/arch/um/sys-x86_64/signal.c
+++ b/trunk/arch/um/sys-x86_64/signal.c
@@ -4,11 +4,11 @@
* Licensed under the GPL
*/
-#include
-#include
-#include
-#include
-#include
+#include "linux/personality.h"
+#include "linux/ptrace.h"
+#include "asm/unistd.h"
+#include "asm/uaccess.h"
+#include "asm/ucontext.h"
#include "frame_kern.h"
#include "skas.h"
@@ -27,16 +27,16 @@ void copy_sc(struct uml_pt_regs *regs, void *from)
GETREG(regs, R13, sc, r13);
GETREG(regs, R14, sc, r14);
GETREG(regs, R15, sc, r15);
- GETREG(regs, RDI, sc, di);
- GETREG(regs, RSI, sc, si);
- GETREG(regs, RBP, sc, bp);
- GETREG(regs, RBX, sc, bx);
- GETREG(regs, RDX, sc, dx);
- GETREG(regs, RAX, sc, ax);
- GETREG(regs, RCX, sc, cx);
- GETREG(regs, RSP, sc, sp);
- GETREG(regs, RIP, sc, ip);
- GETREG(regs, EFLAGS, sc, flags);
+ GETREG(regs, RDI, sc, rdi);
+ GETREG(regs, RSI, sc, rsi);
+ GETREG(regs, RBP, sc, rbp);
+ GETREG(regs, RBX, sc, rbx);
+ GETREG(regs, RDX, sc, rdx);
+ GETREG(regs, RAX, sc, rax);
+ GETREG(regs, RCX, sc, rcx);
+ GETREG(regs, RSP, sc, rsp);
+ GETREG(regs, RIP, sc, rip);
+ GETREG(regs, EFLAGS, sc, eflags);
GETREG(regs, CS, sc, cs);
#undef GETREG
@@ -61,16 +61,16 @@ static int copy_sc_from_user(struct pt_regs *regs,
err |= GETREG(regs, R13, from, r13);
err |= GETREG(regs, R14, from, r14);
err |= GETREG(regs, R15, from, r15);
- err |= GETREG(regs, RDI, from, di);
- err |= GETREG(regs, RSI, from, si);
- err |= GETREG(regs, RBP, from, bp);
- err |= GETREG(regs, RBX, from, bx);
- err |= GETREG(regs, RDX, from, dx);
- err |= GETREG(regs, RAX, from, ax);
- err |= GETREG(regs, RCX, from, cx);
- err |= GETREG(regs, RSP, from, sp);
- err |= GETREG(regs, RIP, from, ip);
- err |= GETREG(regs, EFLAGS, from, flags);
+ err |= GETREG(regs, RDI, from, rdi);
+ err |= GETREG(regs, RSI, from, rsi);
+ err |= GETREG(regs, RBP, from, rbp);
+ err |= GETREG(regs, RBX, from, rbx);
+ err |= GETREG(regs, RDX, from, rdx);
+ err |= GETREG(regs, RAX, from, rax);
+ err |= GETREG(regs, RCX, from, rcx);
+ err |= GETREG(regs, RSP, from, rsp);
+ err |= GETREG(regs, RIP, from, rip);
+ err |= GETREG(regs, EFLAGS, from, eflags);
err |= GETREG(regs, CS, from, cs);
if (err)
return 1;
@@ -108,19 +108,19 @@ static int copy_sc_to_user(struct sigcontext __user *to,
__put_user((regs)->regs.gp[(regno) / sizeof(unsigned long)], \
&(sc)->regname)
- err |= PUTREG(regs, RDI, to, di);
- err |= PUTREG(regs, RSI, to, si);
- err |= PUTREG(regs, RBP, to, bp);
+ err |= PUTREG(regs, RDI, to, rdi);
+ err |= PUTREG(regs, RSI, to, rsi);
+ err |= PUTREG(regs, RBP, to, rbp);
/*
* Must use orignal RSP, which is passed in, rather than what's in
* the pt_regs, because that's already been updated to point at the
* signal frame.
*/
- err |= __put_user(sp, &to->sp);
- err |= PUTREG(regs, RBX, to, bx);
- err |= PUTREG(regs, RDX, to, dx);
- err |= PUTREG(regs, RCX, to, cx);
- err |= PUTREG(regs, RAX, to, ax);
+ err |= __put_user(sp, &to->rsp);
+ err |= PUTREG(regs, RBX, to, rbx);
+ err |= PUTREG(regs, RDX, to, rdx);
+ err |= PUTREG(regs, RCX, to, rcx);
+ err |= PUTREG(regs, RAX, to, rax);
err |= PUTREG(regs, R8, to, r8);
err |= PUTREG(regs, R9, to, r9);
err |= PUTREG(regs, R10, to, r10);
@@ -135,8 +135,8 @@ static int copy_sc_to_user(struct sigcontext __user *to,
err |= __put_user(fi->error_code, &to->err);
err |= __put_user(fi->trap_no, &to->trapno);
- err |= PUTREG(regs, RIP, to, ip);
- err |= PUTREG(regs, EFLAGS, to, flags);
+ err |= PUTREG(regs, RIP, to, rip);
+ err |= PUTREG(regs, EFLAGS, to, eflags);
#undef PUTREG
err |= __put_user(mask, &to->oldmask);
diff --git a/trunk/arch/x86/Kconfig b/trunk/arch/x86/Kconfig
index fb3eea3e38ee..80b7ba4056db 100644
--- a/trunk/arch/x86/Kconfig
+++ b/trunk/arch/x86/Kconfig
@@ -17,69 +17,81 @@ config X86_64
### Arch settings
config X86
- def_bool y
-
-config GENERIC_LOCKBREAK
- def_bool n
+ bool
+ default y
config GENERIC_TIME
- def_bool y
+ bool
+ default y
config GENERIC_CMOS_UPDATE
- def_bool y
+ bool
+ default y
config CLOCKSOURCE_WATCHDOG
- def_bool y
+ bool
+ default y
config GENERIC_CLOCKEVENTS
- def_bool y
+ bool
+ default y
config GENERIC_CLOCKEVENTS_BROADCAST
- def_bool y
+ bool
+ default y
depends on X86_64 || (X86_32 && X86_LOCAL_APIC)
config LOCKDEP_SUPPORT
- def_bool y
+ bool
+ default y
config STACKTRACE_SUPPORT
- def_bool y
+ bool
+ default y
config SEMAPHORE_SLEEPERS
- def_bool y
+ bool
+ default y
config MMU
- def_bool y
+ bool
+ default y
config ZONE_DMA
- def_bool y
+ bool
+ default y
config QUICKLIST
- def_bool X86_32
+ bool
+ default X86_32
config SBUS
bool
config GENERIC_ISA_DMA
- def_bool y
+ bool
+ default y
config GENERIC_IOMAP
- def_bool y
+ bool
+ default y
config GENERIC_BUG
- def_bool y
+ bool
+ default y
depends on BUG
config GENERIC_HWEIGHT
- def_bool y
-
-config GENERIC_GPIO
- def_bool n
+ bool
+ default y
config ARCH_MAY_HAVE_PC_FDC
- def_bool y
+ bool
+ default y
config DMI
- def_bool y
+ bool
+ default y
config RWSEM_GENERIC_SPINLOCK
def_bool !X86_XADD
@@ -100,9 +112,6 @@ config GENERIC_TIME_VSYSCALL
bool
default X86_64
-config HAVE_SETUP_PER_CPU_AREA
- def_bool X86_64
-
config ARCH_SUPPORTS_OPROFILE
bool
default y
@@ -135,17 +144,9 @@ config GENERIC_PENDING_IRQ
config X86_SMP
bool
- depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64)
+ depends on X86_32 && SMP && !X86_VOYAGER
default y
-config X86_32_SMP
- def_bool y
- depends on X86_32 && SMP
-
-config X86_64_SMP
- def_bool y
- depends on X86_64 && SMP
-
config X86_HT
bool
depends on SMP
@@ -291,18 +292,6 @@ config X86_ES7000
Only choose this option if you have such a system, otherwise you
should say N here.
-config X86_RDC321X
- bool "RDC R-321x SoC"
- depends on X86_32
- select M486
- select X86_REBOOTFIXUPS
- select GENERIC_GPIO
- select LEDS_GPIO
- help
- This option is needed for RDC R-321x system-on-chip, also known
- as R-8610-(G).
- If you don't have one of these chips, you should say N here.
-
config X86_VSMP
bool "Support for ScaleMP vSMP"
depends on X86_64 && PCI
@@ -314,8 +303,8 @@ config X86_VSMP
endchoice
config SCHED_NO_NO_OMIT_FRAME_POINTER
- def_bool y
- prompt "Single-depth WCHAN output"
+ bool "Single-depth WCHAN output"
+ default y
depends on X86_32
help
Calculate simpler /proc//wchan values. If this option
@@ -325,8 +314,18 @@ config SCHED_NO_NO_OMIT_FRAME_POINTER
If in doubt, say "Y".
+config PARAVIRT
+ bool
+ depends on X86_32 && !(X86_VISWS || X86_VOYAGER)
+ help
+ This changes the kernel so it can modify itself when it is run
+ under a hypervisor, potentially improving performance significantly
+ over full virtualization. However, when run without a hypervisor
+ the kernel is theoretically slower and slightly larger.
+
menuconfig PARAVIRT_GUEST
bool "Paravirtualized guest support"
+ depends on X86_32
help
Say Y here to get to see options related to running Linux under
various hypervisors. This option alone does not add any kernel code.
@@ -340,7 +339,6 @@ source "arch/x86/xen/Kconfig"
config VMI
bool "VMI Guest support"
select PARAVIRT
- depends on X86_32
depends on !(X86_VISWS || X86_VOYAGER)
help
VMI provides a paravirtualized interface to the VMware ESX server
@@ -350,43 +348,40 @@ config VMI
source "arch/x86/lguest/Kconfig"
-config PARAVIRT
- bool "Enable paravirtualization code"
- depends on !(X86_VISWS || X86_VOYAGER)
- help
- This changes the kernel so it can modify itself when it is run
- under a hypervisor, potentially improving performance significantly
- over full virtualization. However, when run without a hypervisor
- the kernel is theoretically slower and slightly larger.
-
endif
config ACPI_SRAT
- def_bool y
+ bool
+ default y
depends on X86_32 && ACPI && NUMA && (X86_SUMMIT || X86_GENERICARCH)
select ACPI_NUMA
config HAVE_ARCH_PARSE_SRAT
- def_bool y
- depends on ACPI_SRAT
+ bool
+ default y
+ depends on ACPI_SRAT
config X86_SUMMIT_NUMA
- def_bool y
+ bool
+ default y
depends on X86_32 && NUMA && (X86_SUMMIT || X86_GENERICARCH)
config X86_CYCLONE_TIMER
- def_bool y
+ bool
+ default y
depends on X86_32 && X86_SUMMIT || X86_GENERICARCH
config ES7000_CLUSTERED_APIC
- def_bool y
+ bool
+ default y
depends on SMP && X86_ES7000 && MPENTIUMIII
source "arch/x86/Kconfig.cpu"
config HPET_TIMER
- def_bool X86_64
+ bool
prompt "HPET Timer Support" if X86_32
+ default X86_64
help
Use the IA-PC HPET (High Precision Event Timer) to manage
time in preference to the PIT and RTC, if a HPET is
@@ -404,8 +399,9 @@ config HPET_TIMER
Choose N to continue using the legacy 8254 timer.
config HPET_EMULATE_RTC
- def_bool y
- depends on HPET_TIMER && (RTC=y || RTC=m)
+ bool
+ depends on HPET_TIMER && RTC=y
+ default y
# Mark as embedded because too many people got it wrong.
# The code disables itself when not needed.
@@ -445,8 +441,8 @@ config CALGARY_IOMMU
If unsure, say Y.
config CALGARY_IOMMU_ENABLED_BY_DEFAULT
- def_bool y
- prompt "Should Calgary be enabled by default?"
+ bool "Should Calgary be enabled by default?"
+ default y
depends on CALGARY_IOMMU
help
Should Calgary be enabled by default? if you choose 'y', Calgary
@@ -490,9 +486,9 @@ config SCHED_SMT
N here.
config SCHED_MC
- def_bool y
- prompt "Multi-core scheduler support"
+ bool "Multi-core scheduler support"
depends on (X86_64 && SMP) || (X86_32 && X86_HT)
+ default y
help
Multi-core scheduler support improves the CPU scheduler's decision
making when dealing with multi-core CPU chips at a cost of slightly
@@ -526,16 +522,19 @@ config X86_UP_IOAPIC
an IO-APIC, then the kernel will still run with no slowdown at all.
config X86_LOCAL_APIC
- def_bool y
+ bool
depends on X86_64 || (X86_32 && (X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER) || X86_GENERICARCH))
+ default y
config X86_IO_APIC
- def_bool y
+ bool
depends on X86_64 || (X86_32 && (X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER)) || X86_GENERICARCH))
+ default y
config X86_VISWS_APIC
- def_bool y
+ bool
depends on X86_32 && X86_VISWS
+ default y
config X86_MCE
bool "Machine Check Exception"
@@ -555,17 +554,17 @@ config X86_MCE
the 386 and 486, so nearly everyone can say Y here.
config X86_MCE_INTEL
- def_bool y
- prompt "Intel MCE features"
+ bool "Intel MCE features"
depends on X86_64 && X86_MCE && X86_LOCAL_APIC
+ default y
help
Additional support for intel specific MCE features such as
the thermal monitor.
config X86_MCE_AMD
- def_bool y
- prompt "AMD MCE features"
+ bool "AMD MCE features"
depends on X86_64 && X86_MCE && X86_LOCAL_APIC
+ default y
help
Additional support for AMD specific MCE features such as
the DRAM Error Threshold.
@@ -638,9 +637,9 @@ config I8K
Say N otherwise.
config X86_REBOOTFIXUPS
- def_bool n
- prompt "Enable X86 board specific fixups for reboot"
+ bool "Enable X86 board specific fixups for reboot"
depends on X86_32 && X86
+ default n
---help---
This enables chipset and/or board specific fixups to be done
in order to get reboot to work correctly. This is only needed on
@@ -649,7 +648,7 @@ config X86_REBOOTFIXUPS
system.
Currently, the only fixup is for the Geode machines using
- CS5530A and CS5536 chipsets and the RDC R-321x SoC.
+ CS5530A and CS5536 chipsets.
Say Y if you want to enable the fixup. Currently, it's safe to
enable this option even if you don't need it.
@@ -673,8 +672,9 @@ config MICROCODE
module will be called microcode.
config MICROCODE_OLD_INTERFACE
- def_bool y
+ bool
depends on MICROCODE
+ default y
config X86_MSR
tristate "/dev/cpu/*/msr - Model-specific register support"
@@ -798,12 +798,13 @@ config PAGE_OFFSET
depends on X86_32
config HIGHMEM
- def_bool y
+ bool
depends on X86_32 && (HIGHMEM64G || HIGHMEM4G)
+ default y
config X86_PAE
- def_bool n
- prompt "PAE (Physical Address Extension) Support"
+ bool "PAE (Physical Address Extension) Support"
+ default n
depends on X86_32 && !HIGHMEM4G
select RESOURCES_64BIT
help
@@ -835,10 +836,10 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
depends on X86_32 && X86_SUMMIT && (!HIGHMEM64G || !ACPI)
config K8_NUMA
- def_bool y
- prompt "Old style AMD Opteron NUMA detection"
- depends on X86_64 && NUMA && PCI
- help
+ bool "Old style AMD Opteron NUMA detection"
+ depends on X86_64 && NUMA && PCI
+ default y
+ help
Enable K8 NUMA node topology detection. You should say Y here if
you have a multi processor AMD K8 system. This uses an old
method to read the NUMA configuration directly from the builtin
@@ -846,10 +847,10 @@ config K8_NUMA
instead, which also takes priority if both are compiled in.
config X86_64_ACPI_NUMA
- def_bool y
- prompt "ACPI NUMA detection"
+ bool "ACPI NUMA detection"
depends on X86_64 && NUMA && ACPI && PCI
select ACPI_NUMA
+ default y
help
Enable ACPI SRAT based node topology detection.
@@ -863,53 +864,52 @@ config NUMA_EMU
config NODES_SHIFT
int
- range 1 15 if X86_64
default "6" if X86_64
default "4" if X86_NUMAQ
default "3"
depends on NEED_MULTIPLE_NODES
config HAVE_ARCH_BOOTMEM_NODE
- def_bool y
+ bool
depends on X86_32 && NUMA
+ default y
config ARCH_HAVE_MEMORY_PRESENT
- def_bool y
+ bool
depends on X86_32 && DISCONTIGMEM
+ default y
config NEED_NODE_MEMMAP_SIZE
- def_bool y
+ bool
depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
+ default y
config HAVE_ARCH_ALLOC_REMAP
- def_bool y
+ bool
depends on X86_32 && NUMA
+ default y
config ARCH_FLATMEM_ENABLE
def_bool y
- depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && X86_PC && !NUMA
+ depends on (X86_32 && ARCH_SELECT_MEMORY_MODEL && X86_PC) || (X86_64 && !NUMA)
config ARCH_DISCONTIGMEM_ENABLE
def_bool y
- depends on NUMA && X86_32
+ depends on NUMA
config ARCH_DISCONTIGMEM_DEFAULT
def_bool y
- depends on NUMA && X86_32
-
-config ARCH_SPARSEMEM_DEFAULT
- def_bool y
- depends on X86_64
+ depends on NUMA
config ARCH_SPARSEMEM_ENABLE
def_bool y
- depends on X86_64 || NUMA || (EXPERIMENTAL && X86_PC)
+ depends on NUMA || (EXPERIMENTAL && (X86_PC || X86_64))
select SPARSEMEM_STATIC if X86_32
select SPARSEMEM_VMEMMAP_ENABLE if X86_64
config ARCH_SELECT_MEMORY_MODEL
def_bool y
- depends on ARCH_SPARSEMEM_ENABLE
+ depends on X86_32 && ARCH_SPARSEMEM_ENABLE
config ARCH_MEMORY_PROBE
def_bool X86_64
@@ -987,32 +987,42 @@ config MTRR
See for more information.
config EFI
- def_bool n
- prompt "EFI runtime service support"
- depends on ACPI
+ bool "Boot from EFI support"
+ depends on X86_32 && ACPI
+ default n
---help---
- This enables the kernel to use EFI runtime services that are
+ This enables the kernel to boot on EFI platforms using
+ system configuration information passed to it from the firmware.
+ This also enables the kernel to use any EFI runtime services that are
available (such as the EFI variable services).
- This option is only useful on systems that have EFI firmware.
- In addition, you should use the latest ELILO loader available
- at in order to take advantage
- of EFI runtime services. However, even with this option, the
- resultant kernel should continue to boot on existing non-EFI
- platforms.
+ This option is only useful on systems that have EFI firmware
+ and will result in a kernel image that is ~8k larger. In addition,
+ you must use the latest ELILO loader available at
+ in order to take advantage of
+ kernel initialization using EFI information (neither GRUB nor LILO know
+ anything about EFI). However, even with this option, the resultant
+ kernel should continue to boot on existing non-EFI platforms.
config IRQBALANCE
- def_bool y
- prompt "Enable kernel irq balancing"
+ bool "Enable kernel irq balancing"
depends on X86_32 && SMP && X86_IO_APIC
+ default y
help
The default yes will allow the kernel to do irq load balancing.
Saying no will keep the kernel from doing irq load balancing.
+# turning this on wastes a bunch of space.
+# Summit needs it only when NUMA is on
+config BOOT_IOREMAP
+ bool
+ depends on X86_32 && (((X86_SUMMIT || X86_GENERICARCH) && NUMA) || (X86 && EFI))
+ default y
+
config SECCOMP
- def_bool y
- prompt "Enable seccomp to safely compute untrusted bytecode"
+ bool "Enable seccomp to safely compute untrusted bytecode"
depends on PROC_FS
+ default y
help
This kernel feature is useful for number crunching applications
that may need to compute untrusted bytecode during their
@@ -1179,11 +1189,11 @@ config HOTPLUG_CPU
suspend.
config COMPAT_VDSO
- def_bool y
- prompt "Compat VDSO support"
- depends on X86_32 || IA32_EMULATION
+ bool "Compat VDSO support"
+ default y
+ depends on X86_32
help
- Map the 32-bit VDSO to the predictable old-style address too.
+ Map the VDSO to the predictable old-style address too.
---help---
Say N here if you are running a sufficiently recent glibc
version (2.3.3 or later), to remove the high-mapped
@@ -1197,26 +1207,30 @@ config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y
depends on X86_64 || (X86_32 && HIGHMEM)
+config MEMORY_HOTPLUG_RESERVE
+ def_bool X86_64
+ depends on (MEMORY_HOTPLUG && DISCONTIGMEM)
+
config HAVE_ARCH_EARLY_PFN_TO_NID
def_bool X86_64
depends on NUMA
+config OUT_OF_LINE_PFN_TO_PAGE
+ def_bool X86_64
+ depends on DISCONTIGMEM
+
menu "Power management options"
depends on !X86_VOYAGER
config ARCH_HIBERNATION_HEADER
- def_bool y
+ bool
depends on X86_64 && HIBERNATION
+ default y
source "kernel/power/Kconfig"
source "drivers/acpi/Kconfig"
-config X86_APM_BOOT
- bool
- default y
- depends on APM || APM_MODULE
-
menuconfig APM
tristate "APM (Advanced Power Management) BIOS support"
depends on X86_32 && PM_SLEEP && !X86_VISWS
@@ -1357,7 +1371,7 @@ menu "Bus options (PCI etc.)"
config PCI
bool "PCI support" if !X86_VISWS
depends on !X86_VOYAGER
- default y
+ default y if X86_VISWS
select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC)
help
Find out whether you have a PCI motherboard. PCI is the name of a
@@ -1404,21 +1418,25 @@ config PCI_GOANY
endchoice
config PCI_BIOS
- def_bool y
+ bool
depends on X86_32 && !X86_VISWS && PCI && (PCI_GOBIOS || PCI_GOANY)
+ default y
# x86-64 doesn't support PCI BIOS access from long mode so always go direct.
config PCI_DIRECT
- def_bool y
+ bool
depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY) || X86_VISWS)
+ default y
config PCI_MMCONFIG
- def_bool y
+ bool
depends on X86_32 && PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY)
+ default y
config PCI_DOMAINS
- def_bool y
+ bool
depends on PCI
+ default y
config PCI_MMCONFIG
bool "Support mmconfig PCI config space access"
@@ -1435,9 +1453,9 @@ config DMAR
remapping devices.
config DMAR_GFX_WA
- def_bool y
- prompt "Support for Graphics workaround"
+ bool "Support for Graphics workaround"
depends on DMAR
+ default y
help
Current Graphics drivers tend to use physical address
for DMA and avoid using DMA APIs. Setting this config
@@ -1446,8 +1464,9 @@ config DMAR_GFX_WA
to use physical addresses for DMA.
config DMAR_FLOPPY_WA
- def_bool y
+ bool
depends on DMAR
+ default y
help
Floppy disk drivers are know to bypass DMA API calls
thereby failing to work when IOMMU is enabled. This
@@ -1460,7 +1479,8 @@ source "drivers/pci/Kconfig"
# x86_64 have no ISA slots, but do have ISA-style DMA.
config ISA_DMA_API
- def_bool y
+ bool
+ default y
if X86_32
@@ -1526,9 +1546,9 @@ config SCx200HR_TIMER
other workaround is idle=poll boot option.
config GEODE_MFGPT_TIMER
- def_bool y
- prompt "Geode Multi-Function General Purpose Timer (MFGPT) events"
+ bool "Geode Multi-Function General Purpose Timer (MFGPT) events"
depends on MGEODE_LX && GENERIC_TIME && GENERIC_CLOCKEVENTS
+ default y
help
This driver provides a clock event source based on the MFGPT
timer(s) in the CS5535 and CS5536 companion chip for the geode.
@@ -1555,7 +1575,6 @@ source "fs/Kconfig.binfmt"
config IA32_EMULATION
bool "IA32 Emulation"
depends on X86_64
- select COMPAT_BINFMT_ELF
help
Include code to run 32-bit programs under a 64-bit kernel. You should
likely turn this on, unless you're 100% sure that you don't have any
@@ -1568,16 +1587,18 @@ config IA32_AOUT
Support old a.out binaries in the 32bit emulation.
config COMPAT
- def_bool y
+ bool
depends on IA32_EMULATION
+ default y
config COMPAT_FOR_U64_ALIGNMENT
def_bool COMPAT
depends on X86_64
config SYSVIPC_COMPAT
- def_bool y
+ bool
depends on X86_64 && COMPAT && SYSVIPC
+ default y
endmenu
diff --git a/trunk/arch/x86/Kconfig.cpu b/trunk/arch/x86/Kconfig.cpu
index e09a6b73a1aa..c30162202dc4 100644
--- a/trunk/arch/x86/Kconfig.cpu
+++ b/trunk/arch/x86/Kconfig.cpu
@@ -219,10 +219,10 @@ config MGEODEGX1
Select this for a Geode GX1 (Cyrix MediaGX) chip.
config MGEODE_LX
- bool "Geode GX/LX"
+ bool "Geode GX/LX"
depends on X86_32
- help
- Select this for AMD Geode GX and LX processors.
+ help
+ Select this for AMD Geode GX and LX processors.
config MCYRIXIII
bool "CyrixIII/VIA-C3"
@@ -258,7 +258,7 @@ config MPSC
Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
Xeon CPUs with Intel 64bit which is compatible with x86-64.
Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
- Netburst core and shouldn't use this option. You can distinguish them
+ Netburst core and shouldn't use this option. You can distinguish them
using the cpu family field
in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
@@ -317,75 +317,81 @@ config X86_L1_CACHE_SHIFT
default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7
config X86_XADD
- def_bool y
+ bool
depends on X86_32 && !M386
+ default y
config X86_PPRO_FENCE
- bool "PentiumPro memory ordering errata workaround"
+ bool
depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1
- help
- Old PentiumPro multiprocessor systems had errata that could cause memory
- operations to violate the x86 ordering standard in rare cases. Enabling this
- option will attempt to work around some (but not all) occurances of
- this problem, at the cost of much heavier spinlock and memory barrier
- operations.
-
- If unsure, say n here. Even distro kernels should think twice before enabling
- this: there are few systems, and an unlikely bug.
+ default y
config X86_F00F_BUG
- def_bool y
+ bool
depends on M586MMX || M586TSC || M586 || M486 || M386
+ default y
config X86_WP_WORKS_OK
- def_bool y
+ bool
depends on X86_32 && !M386
+ default y
config X86_INVLPG
- def_bool y
+ bool
depends on X86_32 && !M386
+ default y
config X86_BSWAP
- def_bool y
+ bool
depends on X86_32 && !M386
+ default y
config X86_POPAD_OK
- def_bool y
+ bool
depends on X86_32 && !M386
+ default y
config X86_ALIGNMENT_16
- def_bool y
+ bool
depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
+ default y
config X86_GOOD_APIC
- def_bool y
+ bool
depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || MK8 || MEFFICEON || MCORE2 || MVIAC7 || X86_64
+ default y
config X86_INTEL_USERCOPY
- def_bool y
+ bool
depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
+ default y
config X86_USE_PPRO_CHECKSUM
- def_bool y
+ bool
depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2
+ default y
config X86_USE_3DNOW
- def_bool y
+ bool
depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
+ default y
config X86_OOSTORE
- def_bool y
+ bool
depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR
+ default y
config X86_TSC
- def_bool y
+ bool
depends on ((MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64
+ default y
# this should be set for all -march=.. options where the compiler
# generates cmov.
config X86_CMOV
- def_bool y
+ bool
depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7)
+ default y
config X86_MINIMUM_CPU_FAMILY
int
@@ -393,6 +399,3 @@ config X86_MINIMUM_CPU_FAMILY
default "4" if X86_32 && (X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK)
default "3"
-config X86_DEBUGCTLMSR
- def_bool y
- depends on !(M586MMX || M586TSC || M586 || M486 || M386)
diff --git a/trunk/arch/x86/Kconfig.debug b/trunk/arch/x86/Kconfig.debug
index 2e1e3af28c3a..761ca7b5f120 100644
--- a/trunk/arch/x86/Kconfig.debug
+++ b/trunk/arch/x86/Kconfig.debug
@@ -6,7 +6,7 @@ config TRACE_IRQFLAGS_SUPPORT
source "lib/Kconfig.debug"
config EARLY_PRINTK
- bool "Early printk" if EMBEDDED
+ bool "Early printk" if EMBEDDED && DEBUG_KERNEL && X86_32
default y
help
Write kernel log output directly into the VGA buffer or to a serial
@@ -40,49 +40,22 @@ comment "Page alloc debug is incompatible with Software Suspend on i386"
config DEBUG_PAGEALLOC
bool "Debug page memory allocations"
- depends on DEBUG_KERNEL && X86_32
+ depends on DEBUG_KERNEL && !HIBERNATION && !HUGETLBFS
+ depends on X86_32
help
Unmap pages from the kernel linear mapping after free_pages().
This results in a large slowdown, but helps to find certain types
of memory corruptions.
-config DEBUG_PER_CPU_MAPS
- bool "Debug access to per_cpu maps"
- depends on DEBUG_KERNEL
- depends on X86_64_SMP
- default n
- help
- Say Y to verify that the per_cpu map being accessed has
- been setup. Adds a fair amount of code to kernel memory
- and decreases performance.
-
- Say N if unsure.
-
config DEBUG_RODATA
bool "Write protect kernel read-only data structures"
- default y
depends on DEBUG_KERNEL
help
Mark the kernel read-only data as write-protected in the pagetables,
in order to catch accidental (and incorrect) writes to such const
- data. This is recommended so that we can catch kernel bugs sooner.
- If in doubt, say "Y".
-
-config DEBUG_RODATA_TEST
- bool "Testcase for the DEBUG_RODATA feature"
- depends on DEBUG_RODATA
- help
- This option enables a testcase for the DEBUG_RODATA
- feature as well as for the change_page_attr() infrastructure.
- If in doubt, say "N"
-
-config DEBUG_NX_TEST
- tristate "Testcase for the NX non-executable stack feature"
- depends on DEBUG_KERNEL && m
- help
- This option enables a testcase for the CPU NX capability
- and the software setup of this feature.
- If in doubt, say "N"
+ data. This option may have a slight performance impact because a
+ portion of the kernel code won't be covered by a 2MB TLB anymore.
+ If in doubt, say "N".
config 4KSTACKS
bool "Use 4Kb for kernel stacks instead of 8Kb"
@@ -102,7 +75,8 @@ config X86_FIND_SMP_CONFIG
config X86_MPPARSE
def_bool y
- depends on (X86_32 && (X86_LOCAL_APIC && !X86_VISWS)) || X86_64
+ depends on X86_LOCAL_APIC && !X86_VISWS
+ depends on X86_32
config DOUBLEFAULT
default y
@@ -138,91 +112,4 @@ config IOMMU_LEAK
Add a simple leak tracer to the IOMMU code. This is useful when you
are debugging a buggy device driver that leaks IOMMU mappings.
-#
-# IO delay types:
-#
-
-config IO_DELAY_TYPE_0X80
- int
- default "0"
-
-config IO_DELAY_TYPE_0XED
- int
- default "1"
-
-config IO_DELAY_TYPE_UDELAY
- int
- default "2"
-
-config IO_DELAY_TYPE_NONE
- int
- default "3"
-
-choice
- prompt "IO delay type"
- default IO_DELAY_0XED
-
-config IO_DELAY_0X80
- bool "port 0x80 based port-IO delay [recommended]"
- help
- This is the traditional Linux IO delay used for in/out_p.
- It is the most tested hence safest selection here.
-
-config IO_DELAY_0XED
- bool "port 0xed based port-IO delay"
- help
- Use port 0xed as the IO delay. This frees up port 0x80 which is
- often used as a hardware-debug port.
-
-config IO_DELAY_UDELAY
- bool "udelay based port-IO delay"
- help
- Use udelay(2) as the IO delay method. This provides the delay
- while not having any side-effect on the IO port space.
-
-config IO_DELAY_NONE
- bool "no port-IO delay"
- help
- No port-IO delay. Will break on old boxes that require port-IO
- delay for certain operations. Should work on most new machines.
-
-endchoice
-
-if IO_DELAY_0X80
-config DEFAULT_IO_DELAY_TYPE
- int
- default IO_DELAY_TYPE_0X80
-endif
-
-if IO_DELAY_0XED
-config DEFAULT_IO_DELAY_TYPE
- int
- default IO_DELAY_TYPE_0XED
-endif
-
-if IO_DELAY_UDELAY
-config DEFAULT_IO_DELAY_TYPE
- int
- default IO_DELAY_TYPE_UDELAY
-endif
-
-if IO_DELAY_NONE
-config DEFAULT_IO_DELAY_TYPE
- int
- default IO_DELAY_TYPE_NONE
-endif
-
-config DEBUG_BOOT_PARAMS
- bool "Debug boot parameters"
- depends on DEBUG_KERNEL
- depends on DEBUG_FS
- help
- This option will cause struct boot_params to be exported via debugfs.
-
-config CPA_DEBUG
- bool "CPA self test code"
- depends on DEBUG_KERNEL
- help
- Do change_page_attr self tests at boot.
-
endmenu
diff --git a/trunk/arch/x86/Makefile b/trunk/arch/x86/Makefile
index b08f18261df6..7aa1dc6d67c8 100644
--- a/trunk/arch/x86/Makefile
+++ b/trunk/arch/x86/Makefile
@@ -7,252 +7,13 @@ else
KBUILD_DEFCONFIG := $(ARCH)_defconfig
endif
-# BITS is used as extension for files which are available in a 32 bit
-# and a 64 bit version to simplify shared Makefiles.
-# e.g.: obj-y += foo_$(BITS).o
-export BITS
+# No need to remake these files
+$(srctree)/arch/x86/Makefile%: ;
ifeq ($(CONFIG_X86_32),y)
- BITS := 32
UTS_MACHINE := i386
- CHECKFLAGS += -D__i386__
-
- biarch := $(call cc-option,-m32)
- KBUILD_AFLAGS += $(biarch)
- KBUILD_CFLAGS += $(biarch)
-
- ifdef CONFIG_RELOCATABLE
- LDFLAGS_vmlinux := --emit-relocs
- endif
-
- KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
-
- # prevent gcc from keeping the stack 16 byte aligned
- KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
-
- # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
- # a lot more stack due to the lack of sharing of stacklots:
- KBUILD_CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then \
- echo $(call cc-option,-fno-unit-at-a-time); fi ;)
-
- # CPU-specific tuning. Anything which can be shared with UML should go here.
- include $(srctree)/arch/x86/Makefile_32.cpu
- KBUILD_CFLAGS += $(cflags-y)
-
- # temporary until string.h is fixed
- KBUILD_CFLAGS += -ffreestanding
+ include $(srctree)/arch/x86/Makefile_32
else
- BITS := 64
UTS_MACHINE := x86_64
- CHECKFLAGS += -D__x86_64__ -m64
-
- KBUILD_AFLAGS += -m64
- KBUILD_CFLAGS += -m64
-
- # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
- cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
- cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
-
- cflags-$(CONFIG_MCORE2) += \
- $(call cc-option,-march=core2,$(call cc-option,-mtune=generic))
- cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
- KBUILD_CFLAGS += $(cflags-y)
-
- KBUILD_CFLAGS += -mno-red-zone
- KBUILD_CFLAGS += -mcmodel=kernel
-
- # -funit-at-a-time shrinks the kernel .text considerably
- # unfortunately it makes reading oopses harder.
- KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
-
- # this works around some issues with generating unwind tables in older gccs
- # newer gccs do it by default
- KBUILD_CFLAGS += -maccumulate-outgoing-args
-
- stackp := $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh
- stackp-$(CONFIG_CC_STACKPROTECTOR) := $(shell $(stackp) \
- "$(CC)" -fstack-protector )
- stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(stackp) \
- "$(CC)" -fstack-protector-all )
-
- KBUILD_CFLAGS += $(stackp-y)
-endif
-
-# Stackpointer is addressed different for 32 bit and 64 bit x86
-sp-$(CONFIG_X86_32) := esp
-sp-$(CONFIG_X86_64) := rsp
-
-# do binutils support CFI?
-cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
-# is .cfi_signal_frame supported too?
-cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe)
-
-LDFLAGS := -m elf_$(UTS_MACHINE)
-OBJCOPYFLAGS := -O binary -R .note -R .comment -S
-
-# Speed up the build
-KBUILD_CFLAGS += -pipe
-# Workaround for a gcc prelease that unfortunately was shipped in a suse release
-KBUILD_CFLAGS += -Wno-sign-compare
-#
-KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-# prevent gcc from generating any FP code by mistake
-KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
-
-###
-# Sub architecture support
-# fcore-y is linked before mcore-y files.
-
-# Default subarch .c files
-mcore-y := arch/x86/mach-default/
-
-# Voyager subarch support
-mflags-$(CONFIG_X86_VOYAGER) := -Iinclude/asm-x86/mach-voyager
-mcore-$(CONFIG_X86_VOYAGER) := arch/x86/mach-voyager/
-
-# VISWS subarch support
-mflags-$(CONFIG_X86_VISWS) := -Iinclude/asm-x86/mach-visws
-mcore-$(CONFIG_X86_VISWS) := arch/x86/mach-visws/
-
-# NUMAQ subarch support
-mflags-$(CONFIG_X86_NUMAQ) := -Iinclude/asm-x86/mach-numaq
-mcore-$(CONFIG_X86_NUMAQ) := arch/x86/mach-default/
-
-# BIGSMP subarch support
-mflags-$(CONFIG_X86_BIGSMP) := -Iinclude/asm-x86/mach-bigsmp
-mcore-$(CONFIG_X86_BIGSMP) := arch/x86/mach-default/
-
-#Summit subarch support
-mflags-$(CONFIG_X86_SUMMIT) := -Iinclude/asm-x86/mach-summit
-mcore-$(CONFIG_X86_SUMMIT) := arch/x86/mach-default/
-
-# generic subarchitecture
-mflags-$(CONFIG_X86_GENERICARCH):= -Iinclude/asm-x86/mach-generic
-fcore-$(CONFIG_X86_GENERICARCH) += arch/x86/mach-generic/
-mcore-$(CONFIG_X86_GENERICARCH) := arch/x86/mach-default/
-
-
-# ES7000 subarch support
-mflags-$(CONFIG_X86_ES7000) := -Iinclude/asm-x86/mach-es7000
-fcore-$(CONFIG_X86_ES7000) := arch/x86/mach-es7000/
-mcore-$(CONFIG_X86_ES7000) := arch/x86/mach-default/
-
-# RDC R-321x subarch support
-mflags-$(CONFIG_X86_RDC321X) := -Iinclude/asm-x86/mach-rdc321x
-mcore-$(CONFIG_X86_RDC321X) := arch/x86/mach-default
-core-$(CONFIG_X86_RDC321X) += arch/x86/mach-rdc321x/
-
-# default subarch .h files
-mflags-y += -Iinclude/asm-x86/mach-default
-
-# 64 bit does not support subarch support - clear sub arch variables
-fcore-$(CONFIG_X86_64) :=
-mcore-$(CONFIG_X86_64) :=
-mflags-$(CONFIG_X86_64) :=
-
-KBUILD_CFLAGS += $(mflags-y)
-KBUILD_AFLAGS += $(mflags-y)
-
-###
-# Kernel objects
-
-head-y := arch/x86/kernel/head_$(BITS).o
-head-$(CONFIG_X86_64) += arch/x86/kernel/head64.o
-head-y += arch/x86/kernel/init_task.o
-
-libs-y += arch/x86/lib/
-
-# Sub architecture files that needs linking first
-core-y += $(fcore-y)
-
-# Xen paravirtualization support
-core-$(CONFIG_XEN) += arch/x86/xen/
-
-# lguest paravirtualization support
-core-$(CONFIG_LGUEST_GUEST) += arch/x86/lguest/
-
-core-y += arch/x86/kernel/
-core-y += arch/x86/mm/
-
-# Remaining sub architecture files
-core-y += $(mcore-y)
-
-core-y += arch/x86/crypto/
-core-y += arch/x86/vdso/
-core-$(CONFIG_IA32_EMULATION) += arch/x86/ia32/
-
-# drivers-y are linked after core-y
-drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
-drivers-$(CONFIG_PCI) += arch/x86/pci/
-
-# must be linked after kernel/
-drivers-$(CONFIG_OPROFILE) += arch/x86/oprofile/
-
-ifeq ($(CONFIG_X86_32),y)
-drivers-$(CONFIG_PM) += arch/x86/power/
-drivers-$(CONFIG_FB) += arch/x86/video/
+ include $(srctree)/arch/x86/Makefile_64
endif
-
-####
-# boot loader support. Several targets are kept for legacy purposes
-
-boot := arch/x86/boot
-
-PHONY += zImage bzImage compressed zlilo bzlilo \
- zdisk bzdisk fdimage fdimage144 fdimage288 isoimage install
-
-# Default kernel to build
-all: bzImage
-
-# KBUILD_IMAGE specify target image being built
- KBUILD_IMAGE := $(boot)/bzImage
-zImage zlilo zdisk: KBUILD_IMAGE := arch/x86/boot/zImage
-
-zImage bzImage: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE)
- $(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot
- $(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/bzImage
-
-compressed: zImage
-
-zlilo bzlilo: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zlilo
-
-zdisk bzdisk: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zdisk
-
-fdimage fdimage144 fdimage288 isoimage: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@
-
-install: vdso_install
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) install
-
-PHONY += vdso_install
-vdso_install:
- $(Q)$(MAKE) $(build)=arch/x86/vdso $@
-
-archclean:
- $(Q)rm -rf $(objtree)/arch/i386
- $(Q)rm -rf $(objtree)/arch/x86_64
- $(Q)$(MAKE) $(clean)=$(boot)
-
-define archhelp
- echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
- echo ' install - Install kernel using'
- echo ' (your) ~/bin/installkernel or'
- echo ' (distribution) /sbin/installkernel or'
- echo ' install to $$(INSTALL_PATH) and run lilo'
- echo ' fdimage - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)'
- echo ' fdimage144 - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)'
- echo ' fdimage288 - Create 2.8MB boot floppy image (arch/x86/boot/fdimage)'
- echo ' isoimage - Create a boot CD-ROM image (arch/x86/boot/image.iso)'
- echo ' bzdisk/fdimage*/isoimage also accept:'
- echo ' FDARGS="..." arguments for the booted kernel'
- echo ' FDINITRD=file initrd for the booted kernel'
-endef
-
-CLEAN_FILES += arch/x86/boot/fdimage \
- arch/x86/boot/image.iso \
- arch/x86/boot/mtools.conf
diff --git a/trunk/arch/x86/Makefile_32 b/trunk/arch/x86/Makefile_32
new file mode 100644
index 000000000000..50394da2f6c1
--- /dev/null
+++ b/trunk/arch/x86/Makefile_32
@@ -0,0 +1,175 @@
+#
+# i386 Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" cleaning up for this architecture.
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+#
+# 19990713 Artur Skawina
+# Added '-march' and '-mpreferred-stack-boundary' support
+#
+# 20050320 Kianusch Sayah Karadji
+# Added support for GEODE CPU
+
+# BITS is used as extension for files which are available in a 32 bit
+# and a 64 bit version to simplify shared Makefiles.
+# e.g.: obj-y += foo_$(BITS).o
+BITS := 32
+export BITS
+
+HAS_BIARCH := $(call cc-option-yn, -m32)
+ifeq ($(HAS_BIARCH),y)
+AS := $(AS) --32
+LD := $(LD) -m elf_i386
+CC := $(CC) -m32
+endif
+
+LDFLAGS := -m elf_i386
+OBJCOPYFLAGS := -O binary -R .note -R .comment -S
+ifdef CONFIG_RELOCATABLE
+LDFLAGS_vmlinux := --emit-relocs
+endif
+CHECKFLAGS += -D__i386__
+
+KBUILD_CFLAGS += -pipe -msoft-float -mregparm=3 -freg-struct-return
+
+# prevent gcc from keeping the stack 16 byte aligned
+KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
+
+# CPU-specific tuning. Anything which can be shared with UML should go here.
+include $(srctree)/arch/x86/Makefile_32.cpu
+
+# temporary until string.h is fixed
+cflags-y += -ffreestanding
+
+# this works around some issues with generating unwind tables in older gccs
+# newer gccs do it by default
+cflags-y += -maccumulate-outgoing-args
+
+# Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
+# a lot more stack due to the lack of sharing of stacklots:
+KBUILD_CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then echo $(call cc-option,-fno-unit-at-a-time); fi ;)
+
+# do binutils support CFI?
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_rel_offset esp${comma}0\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+KBUILD_AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_rel_offset esp${comma}0\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+
+# is .cfi_signal_frame supported too?
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,)
+KBUILD_AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,)
+
+KBUILD_CFLAGS += $(cflags-y)
+
+# Default subarch .c files
+mcore-y := arch/x86/mach-default
+
+# Voyager subarch support
+mflags-$(CONFIG_X86_VOYAGER) := -Iinclude/asm-x86/mach-voyager
+mcore-$(CONFIG_X86_VOYAGER) := arch/x86/mach-voyager
+
+# VISWS subarch support
+mflags-$(CONFIG_X86_VISWS) := -Iinclude/asm-x86/mach-visws
+mcore-$(CONFIG_X86_VISWS) := arch/x86/mach-visws
+
+# NUMAQ subarch support
+mflags-$(CONFIG_X86_NUMAQ) := -Iinclude/asm-x86/mach-numaq
+mcore-$(CONFIG_X86_NUMAQ) := arch/x86/mach-default
+
+# BIGSMP subarch support
+mflags-$(CONFIG_X86_BIGSMP) := -Iinclude/asm-x86/mach-bigsmp
+mcore-$(CONFIG_X86_BIGSMP) := arch/x86/mach-default
+
+#Summit subarch support
+mflags-$(CONFIG_X86_SUMMIT) := -Iinclude/asm-x86/mach-summit
+mcore-$(CONFIG_X86_SUMMIT) := arch/x86/mach-default
+
+# generic subarchitecture
+mflags-$(CONFIG_X86_GENERICARCH) := -Iinclude/asm-x86/mach-generic
+mcore-$(CONFIG_X86_GENERICARCH) := arch/x86/mach-default
+core-$(CONFIG_X86_GENERICARCH) += arch/x86/mach-generic/
+
+# ES7000 subarch support
+mflags-$(CONFIG_X86_ES7000) := -Iinclude/asm-x86/mach-es7000
+mcore-$(CONFIG_X86_ES7000) := arch/x86/mach-default
+core-$(CONFIG_X86_ES7000) := arch/x86/mach-es7000/
+
+# Xen paravirtualization support
+core-$(CONFIG_XEN) += arch/x86/xen/
+
+# lguest paravirtualization support
+core-$(CONFIG_LGUEST_GUEST) += arch/x86/lguest/
+
+# default subarch .h files
+mflags-y += -Iinclude/asm-x86/mach-default
+
+head-y := arch/x86/kernel/head_32.o arch/x86/kernel/init_task.o
+
+libs-y += arch/x86/lib/
+core-y += arch/x86/kernel/ \
+ arch/x86/mm/ \
+ $(mcore-y)/ \
+ arch/x86/crypto/
+drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
+drivers-$(CONFIG_PCI) += arch/x86/pci/
+# must be linked after kernel/
+drivers-$(CONFIG_OPROFILE) += arch/x86/oprofile/
+drivers-$(CONFIG_PM) += arch/x86/power/
+drivers-$(CONFIG_FB) += arch/x86/video/
+
+KBUILD_CFLAGS += $(mflags-y)
+KBUILD_AFLAGS += $(mflags-y)
+
+boot := arch/x86/boot
+
+PHONY += zImage bzImage compressed zlilo bzlilo \
+ zdisk bzdisk fdimage fdimage144 fdimage288 isoimage install
+
+all: bzImage
+
+# KBUILD_IMAGE specify target image being built
+ KBUILD_IMAGE := $(boot)/bzImage
+zImage zlilo zdisk: KBUILD_IMAGE := arch/x86/boot/zImage
+
+zImage bzImage: vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE)
+ $(Q)mkdir -p $(objtree)/arch/i386/boot
+ $(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/i386/boot/bzImage
+
+compressed: zImage
+
+zlilo bzlilo: vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zlilo
+
+zdisk bzdisk: vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zdisk
+
+fdimage fdimage144 fdimage288 isoimage: vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@
+
+install:
+ $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) install
+
+archclean:
+ $(Q)rm -rf $(objtree)/arch/i386/boot
+ $(Q)$(MAKE) $(clean)=arch/x86/boot
+
+define archhelp
+ echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
+ echo ' install - Install kernel using'
+ echo ' (your) ~/bin/installkernel or'
+ echo ' (distribution) /sbin/installkernel or'
+ echo ' install to $$(INSTALL_PATH) and run lilo'
+ echo ' bzdisk - Create a boot floppy in /dev/fd0'
+ echo ' fdimage - Create a boot floppy image'
+ echo ' isoimage - Create a boot CD-ROM image'
+endef
+
+CLEAN_FILES += arch/x86/boot/fdimage \
+ arch/x86/boot/image.iso \
+ arch/x86/boot/mtools.conf
diff --git a/trunk/arch/x86/Makefile_64 b/trunk/arch/x86/Makefile_64
new file mode 100644
index 000000000000..a804860022e6
--- /dev/null
+++ b/trunk/arch/x86/Makefile_64
@@ -0,0 +1,144 @@
+#
+# x86_64 Makefile
+#
+# This file is included by the global makefile so that you can add your own
+# architecture-specific flags and dependencies. Remember to do have actions
+# for "archclean" and "archdep" for cleaning up and making dependencies for
+# this architecture
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+#
+# 19990713 Artur Skawina
+# Added '-march' and '-mpreferred-stack-boundary' support
+# 20000913 Pavel Machek
+# Converted for x86_64 architecture
+# 20010105 Andi Kleen, add IA32 compiler.
+# ....and later removed it again....
+#
+# $Id: Makefile,v 1.31 2002/03/22 15:56:07 ak Exp $
+
+# BITS is used as extension for files which are available in a 32 bit
+# and a 64 bit version to simplify shared Makefiles.
+# e.g.: obj-y += foo_$(BITS).o
+BITS := 64
+export BITS
+
+LDFLAGS := -m elf_x86_64
+OBJCOPYFLAGS := -O binary -R .note -R .comment -S
+LDFLAGS_vmlinux :=
+CHECKFLAGS += -D__x86_64__ -m64
+
+cflags-y :=
+cflags-kernel-y :=
+cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
+cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
+# gcc doesn't support -march=core2 yet as of gcc 4.3, but I hope it
+# will eventually. Use -mtune=generic as fallback
+cflags-$(CONFIG_MCORE2) += \
+ $(call cc-option,-march=core2,$(call cc-option,-mtune=generic))
+cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
+
+cflags-y += -m64
+cflags-y += -mno-red-zone
+cflags-y += -mcmodel=kernel
+cflags-y += -pipe
+cflags-y += -Wno-sign-compare
+cflags-y += -fno-asynchronous-unwind-tables
+ifneq ($(CONFIG_DEBUG_INFO),y)
+# -fweb shrinks the kernel a bit, but the difference is very small
+# it also messes up debugging, so don't use it for now.
+#cflags-y += $(call cc-option,-fweb)
+endif
+# -funit-at-a-time shrinks the kernel .text considerably
+# unfortunately it makes reading oopses harder.
+cflags-y += $(call cc-option,-funit-at-a-time)
+# prevent gcc from generating any FP code by mistake
+cflags-y += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
+# this works around some issues with generating unwind tables in older gccs
+# newer gccs do it by default
+cflags-y += -maccumulate-outgoing-args
+
+# do binutils support CFI?
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_rel_offset rsp${comma}0\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+KBUILD_AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_rel_offset rsp${comma}0\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+
+# is .cfi_signal_frame supported too?
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,)
+KBUILD_AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,)
+
+cflags-$(CONFIG_CC_STACKPROTECTOR) += $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh "$(CC)" -fstack-protector )
+cflags-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh "$(CC)" -fstack-protector-all )
+
+KBUILD_CFLAGS += $(cflags-y)
+CFLAGS_KERNEL += $(cflags-kernel-y)
+KBUILD_AFLAGS += -m64
+
+head-y := arch/x86/kernel/head_64.o arch/x86/kernel/head64.o arch/x86/kernel/init_task.o
+
+libs-y += arch/x86/lib/
+core-y += arch/x86/kernel/ \
+ arch/x86/mm/ \
+ arch/x86/crypto/ \
+ arch/x86/vdso/
+core-$(CONFIG_IA32_EMULATION) += arch/x86/ia32/
+drivers-$(CONFIG_PCI) += arch/x86/pci/
+drivers-$(CONFIG_OPROFILE) += arch/x86/oprofile/
+
+boot := arch/x86/boot
+
+PHONY += bzImage bzlilo install archmrproper \
+ fdimage fdimage144 fdimage288 isoimage archclean
+
+#Default target when executing "make"
+all: bzImage
+
+BOOTIMAGE := arch/x86/boot/bzImage
+KBUILD_IMAGE := $(BOOTIMAGE)
+
+bzImage: vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) $(BOOTIMAGE)
+ $(Q)mkdir -p $(objtree)/arch/x86_64/boot
+ $(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/x86_64/boot/bzImage
+
+bzlilo: vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) zlilo
+
+bzdisk: vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) zdisk
+
+fdimage fdimage144 fdimage288 isoimage: vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@
+
+install: vdso_install
+ $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@
+
+vdso_install:
+ifeq ($(CONFIG_IA32_EMULATION),y)
+ $(Q)$(MAKE) $(build)=arch/x86/ia32 $@
+endif
+ $(Q)$(MAKE) $(build)=arch/x86/vdso $@
+
+archclean:
+ $(Q)rm -rf $(objtree)/arch/x86_64/boot
+ $(Q)$(MAKE) $(clean)=$(boot)
+
+define archhelp
+ echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
+ echo ' install - Install kernel using'
+ echo ' (your) ~/bin/installkernel or'
+ echo ' (distribution) /sbin/installkernel or'
+ echo ' install to $$(INSTALL_PATH) and run lilo'
+ echo ' bzdisk - Create a boot floppy in /dev/fd0'
+ echo ' fdimage - Create a boot floppy image'
+ echo ' isoimage - Create a boot CD-ROM image'
+endef
+
+CLEAN_FILES += arch/x86/boot/fdimage \
+ arch/x86/boot/image.iso \
+ arch/x86/boot/mtools.conf
+
+
diff --git a/trunk/arch/x86/boot/Makefile b/trunk/arch/x86/boot/Makefile
index 349b81a39c40..7a3116ccf387 100644
--- a/trunk/arch/x86/boot/Makefile
+++ b/trunk/arch/x86/boot/Makefile
@@ -28,11 +28,9 @@ SVGA_MODE := -DSVGA_MODE=NORMAL_VGA
targets := vmlinux.bin setup.bin setup.elf zImage bzImage
subdir- := compressed
-setup-y += a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o
+setup-y += a20.o apm.o cmdline.o copy.o cpu.o cpucheck.o edd.o
setup-y += header.o main.o mca.o memory.o pm.o pmjump.o
-setup-y += printf.o string.o tty.o video.o version.o
-setup-$(CONFIG_X86_APM_BOOT) += apm.o
-setup-$(CONFIG_X86_VOYAGER) += voyager.o
+setup-y += printf.o string.o tty.o video.o version.o voyager.o
# The link order of the video-*.o modules can matter. In particular,
# video-vga.o *must* be listed first, followed by video-vesa.o.
@@ -51,7 +49,10 @@ HOSTCFLAGS_build.o := $(LINUXINCLUDE)
# How to compile the 16-bit code. Note we always compile for -march=i386,
# that way we can complain to the user if the CPU is insufficient.
+cflags-$(CONFIG_X86_32) :=
+cflags-$(CONFIG_X86_64) := -m32
KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
+ $(cflags-y) \
-Wall -Wstrict-prototypes \
-march=i386 -mregparm=3 \
-include $(srctree)/$(src)/code16gcc.h \
@@ -61,7 +62,6 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
$(call cc-option, -fno-unit-at-a-time)) \
$(call cc-option, -fno-stack-protector) \
$(call cc-option, -mpreferred-stack-boundary=2)
-KBUILD_CFLAGS += $(call cc-option,-m32)
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
$(obj)/zImage: IMAGE_OFFSET := 0x1000
diff --git a/trunk/arch/x86/boot/apm.c b/trunk/arch/x86/boot/apm.c
index c117c7fb859c..eab50c55a3a5 100644
--- a/trunk/arch/x86/boot/apm.c
+++ b/trunk/arch/x86/boot/apm.c
@@ -19,6 +19,8 @@
#include "boot.h"
+#if defined(CONFIG_APM) || defined(CONFIG_APM_MODULE)
+
int query_apm_bios(void)
{
u16 ax, bx, cx, dx, di;
@@ -93,3 +95,4 @@ int query_apm_bios(void)
return 0;
}
+#endif
diff --git a/trunk/arch/x86/boot/boot.h b/trunk/arch/x86/boot/boot.h
index 7822a4983da2..d2b5adf46512 100644
--- a/trunk/arch/x86/boot/boot.h
+++ b/trunk/arch/x86/boot/boot.h
@@ -109,7 +109,7 @@ typedef unsigned int addr_t;
static inline u8 rdfs8(addr_t addr)
{
u8 v;
- asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
+ asm volatile("movb %%fs:%1,%0" : "=r" (v) : "m" (*(u8 *)addr));
return v;
}
static inline u16 rdfs16(addr_t addr)
@@ -127,21 +127,21 @@ static inline u32 rdfs32(addr_t addr)
static inline void wrfs8(u8 v, addr_t addr)
{
- asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "qi" (v));
+ asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "r" (v));
}
static inline void wrfs16(u16 v, addr_t addr)
{
- asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "ri" (v));
+ asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "r" (v));
}
static inline void wrfs32(u32 v, addr_t addr)
{
- asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "ri" (v));
+ asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "r" (v));
}
static inline u8 rdgs8(addr_t addr)
{
u8 v;
- asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
+ asm volatile("movb %%gs:%1,%0" : "=r" (v) : "m" (*(u8 *)addr));
return v;
}
static inline u16 rdgs16(addr_t addr)
@@ -159,15 +159,15 @@ static inline u32 rdgs32(addr_t addr)
static inline void wrgs8(u8 v, addr_t addr)
{
- asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "qi" (v));
+ asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "r" (v));
}
static inline void wrgs16(u16 v, addr_t addr)
{
- asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "ri" (v));
+ asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "r" (v));
}
static inline void wrgs32(u32 v, addr_t addr)
{
- asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "ri" (v));
+ asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "r" (v));
}
/* Note: these only return true/false, not a signed return value! */
@@ -241,7 +241,6 @@ int query_apm_bios(void);
/* cmdline.c */
int cmdline_find_option(const char *option, char *buffer, int bufsize);
-int cmdline_find_option_bool(const char *option);
/* cpu.c, cpucheck.c */
int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
diff --git a/trunk/arch/x86/boot/cmdline.c b/trunk/arch/x86/boot/cmdline.c
index 680408a0f463..34bb778c4357 100644
--- a/trunk/arch/x86/boot/cmdline.c
+++ b/trunk/arch/x86/boot/cmdline.c
@@ -95,68 +95,3 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize)
return len;
}
-
-/*
- * Find a boolean option (like quiet,noapic,nosmp....)
- *
- * Returns the position of that option (starts counting with 1)
- * or 0 on not found
- */
-int cmdline_find_option_bool(const char *option)
-{
- u32 cmdline_ptr = boot_params.hdr.cmd_line_ptr;
- addr_t cptr;
- char c;
- int pos = 0, wstart = 0;
- const char *opptr = NULL;
- enum {
- st_wordstart, /* Start of word/after whitespace */
- st_wordcmp, /* Comparing this word */
- st_wordskip, /* Miscompare, skip */
- } state = st_wordstart;
-
- if (!cmdline_ptr || cmdline_ptr >= 0x100000)
- return -1; /* No command line, or inaccessible */
-
- cptr = cmdline_ptr & 0xf;
- set_fs(cmdline_ptr >> 4);
-
- while (cptr < 0x10000) {
- c = rdfs8(cptr++);
- pos++;
-
- switch (state) {
- case st_wordstart:
- if (!c)
- return 0;
- else if (myisspace(c))
- break;
-
- state = st_wordcmp;
- opptr = option;
- wstart = pos;
- /* fall through */
-
- case st_wordcmp:
- if (!*opptr)
- if (!c || myisspace(c))
- return wstart;
- else
- state = st_wordskip;
- else if (!c)
- return 0;
- else if (c != *opptr++)
- state = st_wordskip;
- break;
-
- case st_wordskip:
- if (!c)
- return 0;
- else if (myisspace(c))
- state = st_wordstart;
- break;
- }
- }
-
- return 0; /* Buffer overrun */
-}
diff --git a/trunk/arch/x86/boot/compressed/Makefile b/trunk/arch/x86/boot/compressed/Makefile
index fe24ceabd909..52c1db854520 100644
--- a/trunk/arch/x86/boot/compressed/Makefile
+++ b/trunk/arch/x86/boot/compressed/Makefile
@@ -1,63 +1,5 @@
-#
-# linux/arch/x86/boot/compressed/Makefile
-#
-# create a compressed vmlinux image from the original vmlinux
-#
-
-targets := vmlinux vmlinux.bin vmlinux.bin.gz head_$(BITS).o misc.o piggy.o
-
-KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
-KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
-cflags-$(CONFIG_X86_64) := -mcmodel=small
-KBUILD_CFLAGS += $(cflags-y)
-KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
-KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
-
-KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
-
-LDFLAGS := -m elf_$(UTS_MACHINE)
-LDFLAGS_vmlinux := -T
-
-$(obj)/vmlinux: $(src)/vmlinux_$(BITS).lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE
- $(call if_changed,ld)
- @:
-
-$(obj)/vmlinux.bin: vmlinux FORCE
- $(call if_changed,objcopy)
-
-
ifeq ($(CONFIG_X86_32),y)
-targets += vmlinux.bin.all vmlinux.relocs
-hostprogs-y := relocs
-
-quiet_cmd_relocs = RELOCS $@
- cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
-$(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
- $(call if_changed,relocs)
-
-vmlinux.bin.all-y := $(obj)/vmlinux.bin
-vmlinux.bin.all-$(CONFIG_RELOCATABLE) += $(obj)/vmlinux.relocs
-quiet_cmd_relocbin = BUILD $@
- cmd_relocbin = cat $(filter-out FORCE,$^) > $@
-$(obj)/vmlinux.bin.all: $(vmlinux.bin.all-y) FORCE
- $(call if_changed,relocbin)
-
-ifdef CONFIG_RELOCATABLE
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
- $(call if_changed,gzip)
+include ${srctree}/arch/x86/boot/compressed/Makefile_32
else
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
- $(call if_changed,gzip)
+include ${srctree}/arch/x86/boot/compressed/Makefile_64
endif
-LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
-
-else
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
- $(call if_changed,gzip)
-
-LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
-endif
-
-
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE
- $(call if_changed,ld)
diff --git a/trunk/arch/x86/boot/compressed/Makefile_32 b/trunk/arch/x86/boot/compressed/Makefile_32
new file mode 100644
index 000000000000..e43ff7c56e6e
--- /dev/null
+++ b/trunk/arch/x86/boot/compressed/Makefile_32
@@ -0,0 +1,50 @@
+#
+# linux/arch/x86/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+targets := vmlinux vmlinux.bin vmlinux.bin.gz head_32.o misc_32.o piggy.o \
+ vmlinux.bin.all vmlinux.relocs
+EXTRA_AFLAGS := -traditional
+
+LDFLAGS_vmlinux := -T
+hostprogs-y := relocs
+
+KBUILD_CFLAGS := -m32 -D__KERNEL__ $(LINUX_INCLUDE) -O2 \
+ -fno-strict-aliasing -fPIC \
+ $(call cc-option,-ffreestanding) \
+ $(call cc-option,-fno-stack-protector)
+LDFLAGS := -m elf_i386
+
+$(obj)/vmlinux: $(src)/vmlinux_32.lds $(obj)/head_32.o $(obj)/misc_32.o $(obj)/piggy.o FORCE
+ $(call if_changed,ld)
+ @:
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+ $(call if_changed,objcopy)
+
+quiet_cmd_relocs = RELOCS $@
+ cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
+$(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
+ $(call if_changed,relocs)
+
+vmlinux.bin.all-y := $(obj)/vmlinux.bin
+vmlinux.bin.all-$(CONFIG_RELOCATABLE) += $(obj)/vmlinux.relocs
+quiet_cmd_relocbin = BUILD $@
+ cmd_relocbin = cat $(filter-out FORCE,$^) > $@
+$(obj)/vmlinux.bin.all: $(vmlinux.bin.all-y) FORCE
+ $(call if_changed,relocbin)
+
+ifdef CONFIG_RELOCATABLE
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
+ $(call if_changed,gzip)
+else
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,gzip)
+endif
+
+LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
+
+$(obj)/piggy.o: $(src)/vmlinux_32.scr $(obj)/vmlinux.bin.gz FORCE
+ $(call if_changed,ld)
diff --git a/trunk/arch/x86/boot/compressed/Makefile_64 b/trunk/arch/x86/boot/compressed/Makefile_64
new file mode 100644
index 000000000000..7801e8dd90b2
--- /dev/null
+++ b/trunk/arch/x86/boot/compressed/Makefile_64
@@ -0,0 +1,30 @@
+#
+# linux/arch/x86/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+targets := vmlinux vmlinux.bin vmlinux.bin.gz head_64.o misc_64.o piggy.o
+
+KBUILD_CFLAGS := -m64 -D__KERNEL__ $(LINUXINCLUDE) -O2 \
+ -fno-strict-aliasing -fPIC -mcmodel=small \
+ $(call cc-option, -ffreestanding) \
+ $(call cc-option, -fno-stack-protector)
+KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
+LDFLAGS := -m elf_x86_64
+
+LDFLAGS_vmlinux := -T
+$(obj)/vmlinux: $(src)/vmlinux_64.lds $(obj)/head_64.o $(obj)/misc_64.o $(obj)/piggy.o FORCE
+ $(call if_changed,ld)
+ @:
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+ $(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,gzip)
+
+LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
+
+$(obj)/piggy.o: $(obj)/vmlinux_64.scr $(obj)/vmlinux.bin.gz FORCE
+ $(call if_changed,ld)
diff --git a/trunk/arch/x86/boot/compressed/misc.c b/trunk/arch/x86/boot/compressed/misc_32.c
similarity index 86%
rename from trunk/arch/x86/boot/compressed/misc.c
rename to trunk/arch/x86/boot/compressed/misc_32.c
index 8182e32c1b42..b74d60d1b2fa 100644
--- a/trunk/arch/x86/boot/compressed/misc.c
+++ b/trunk/arch/x86/boot/compressed/misc_32.c
@@ -1,7 +1,7 @@
/*
* misc.c
- *
- * This is a collection of several routines from gzip-1.0.3
+ *
+ * This is a collection of several routines from gzip-1.0.3
* adapted for Linux.
*
* malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
@@ -9,18 +9,9 @@
* High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
*/
-/*
- * we have to be careful, because no indirections are allowed here, and
- * paravirt_ops is a kind of one. As it will only run in baremetal anyway,
- * we just keep it from happening
- */
#undef CONFIG_PARAVIRT
-#ifdef CONFIG_X86_64
-#define _LINUX_STRING_H_ 1
-#define __LINUX_BITMAP_H 1
-#endif
-
#include
+#include
#include
#include
#include
@@ -195,20 +186,10 @@ static void *memcpy(void *dest, const void *src, unsigned n);
static void putstr(const char *);
-#ifdef CONFIG_X86_64
-#define memptr long
-#else
-#define memptr unsigned
-#endif
-
-static memptr free_mem_ptr;
-static memptr free_mem_end_ptr;
+static unsigned long free_mem_ptr;
+static unsigned long free_mem_end_ptr;
-#ifdef CONFIG_X86_64
-#define HEAP_SIZE 0x7000
-#else
#define HEAP_SIZE 0x4000
-#endif
static char *vidmem = (char *)0xb8000;
static int vidport;
@@ -249,7 +230,7 @@ static void gzip_mark(void **ptr)
static void gzip_release(void **ptr)
{
- free_mem_ptr = (memptr) *ptr;
+ free_mem_ptr = (unsigned long) *ptr;
}
static void scroll(void)
@@ -266,10 +247,8 @@ static void putstr(const char *s)
int x,y,pos;
char c;
-#ifdef CONFIG_X86_32
if (RM_SCREEN_INFO.orig_video_mode == 0 && lines == 0 && cols == 0)
return;
-#endif
x = RM_SCREEN_INFO.orig_x;
y = RM_SCREEN_INFO.orig_y;
@@ -282,7 +261,7 @@ static void putstr(const char *s)
y--;
}
} else {
- vidmem [(x + cols * y) * 2] = c;
+ vidmem [ ( x + cols * y ) * 2 ] = c;
if ( ++x >= cols ) {
x = 0;
if ( ++y >= lines ) {
@@ -297,16 +276,16 @@ static void putstr(const char *s)
RM_SCREEN_INFO.orig_y = y;
pos = (x + cols * y) * 2; /* Update cursor position */
- outb(14, vidport);
- outb(0xff & (pos >> 9), vidport+1);
- outb(15, vidport);
- outb(0xff & (pos >> 1), vidport+1);
+ outb_p(14, vidport);
+ outb_p(0xff & (pos >> 9), vidport+1);
+ outb_p(15, vidport);
+ outb_p(0xff & (pos >> 1), vidport+1);
}
static void* memset(void* s, int c, unsigned n)
{
int i;
- char *ss = s;
+ char *ss = (char*)s;
for (i=0;i= 0xffffffffffUL)
- error("Destination address too large");
-#else
if ((u32)output & (CONFIG_PHYSICAL_ALIGN -1))
error("Destination address not CONFIG_PHYSICAL_ALIGN aligned");
- if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff))
+ if (end > ((-__PAGE_OFFSET-(512 <<20)-1) & 0x7fffffff))
error("Destination address too large");
#ifndef CONFIG_RELOCATABLE
if ((u32)output != LOAD_PHYSICAL_ADDR)
error("Wrong destination address");
-#endif
#endif
makecrc();
- putstr("\nDecompressing Linux... ");
+ putstr("Uncompressing Linux... ");
gunzip();
- putstr("done.\nBooting the kernel.\n");
+ putstr("Ok, booting the kernel.\n");
return;
}
diff --git a/trunk/arch/x86/boot/compressed/misc_64.c b/trunk/arch/x86/boot/compressed/misc_64.c
new file mode 100644
index 000000000000..6ea015aa65e4
--- /dev/null
+++ b/trunk/arch/x86/boot/compressed/misc_64.c
@@ -0,0 +1,371 @@
+/*
+ * misc.c
+ *
+ * This is a collection of several routines from gzip-1.0.3
+ * adapted for Linux.
+ *
+ * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ * puts by Nick Holloway 1993, better puts by Martin Mares 1995
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+
+#define _LINUX_STRING_H_ 1
+#define __LINUX_BITMAP_H 1
+
+#include
+#include
+#include
+#include
+
+/* WARNING!!
+ * This code is compiled with -fPIC and it is relocated dynamically
+ * at run time, but no relocation processing is performed.
+ * This means that it is not safe to place pointers in static structures.
+ */
+
+/*
+ * Getting to provable safe in place decompression is hard.
+ * Worst case behaviours need to be analyzed.
+ * Background information:
+ *
+ * The file layout is:
+ * magic[2]
+ * method[1]
+ * flags[1]
+ * timestamp[4]
+ * extraflags[1]
+ * os[1]
+ * compressed data blocks[N]
+ * crc[4] orig_len[4]
+ *
+ * resulting in 18 bytes of non compressed data overhead.
+ *
+ * Files divided into blocks
+ * 1 bit (last block flag)
+ * 2 bits (block type)
+ *
+ * 1 block occurs every 32K -1 bytes or when there 50% compression has been achieved.
+ * The smallest block type encoding is always used.
+ *
+ * stored:
+ * 32 bits length in bytes.
+ *
+ * fixed:
+ * magic fixed tree.
+ * symbols.
+ *
+ * dynamic:
+ * dynamic tree encoding.
+ * symbols.
+ *
+ *
+ * The buffer for decompression in place is the length of the
+ * uncompressed data, plus a small amount extra to keep the algorithm safe.
+ * The compressed data is placed at the end of the buffer. The output
+ * pointer is placed at the start of the buffer and the input pointer
+ * is placed where the compressed data starts. Problems will occur
+ * when the output pointer overruns the input pointer.
+ *
+ * The output pointer can only overrun the input pointer if the input
+ * pointer is moving faster than the output pointer. A condition only
+ * triggered by data whose compressed form is larger than the uncompressed
+ * form.
+ *
+ * The worst case at the block level is a growth of the compressed data
+ * of 5 bytes per 32767 bytes.
+ *
+ * The worst case internal to a compressed block is very hard to figure.
+ * The worst case can at least be boundined by having one bit that represents
+ * 32764 bytes and then all of the rest of the bytes representing the very
+ * very last byte.
+ *
+ * All of which is enough to compute an amount of extra data that is required
+ * to be safe. To avoid problems at the block level allocating 5 extra bytes
+ * per 32767 bytes of data is sufficient. To avoind problems internal to a block
+ * adding an extra 32767 bytes (the worst case uncompressed block size) is
+ * sufficient, to ensure that in the worst case the decompressed data for
+ * block will stop the byte before the compressed data for a block begins.
+ * To avoid problems with the compressed data's meta information an extra 18
+ * bytes are needed. Leading to the formula:
+ *
+ * extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size.
+ *
+ * Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
+ * Adding 32768 instead of 32767 just makes for round numbers.
+ * Adding the decompressor_size is necessary as it musht live after all
+ * of the data as well. Last I measured the decompressor is about 14K.
+ * 10K of actual data and 4K of bss.
+ *
+ */
+
+/*
+ * gzip declarations
+ */
+
+#define OF(args) args
+#define STATIC static
+
+#undef memset
+#undef memcpy
+#define memzero(s, n) memset ((s), 0, (n))
+
+typedef unsigned char uch;
+typedef unsigned short ush;
+typedef unsigned long ulg;
+
+#define WSIZE 0x80000000 /* Window size must be at least 32k,
+ * and a power of two
+ * We don't actually have a window just
+ * a huge output buffer so I report
+ * a 2G windows size, as that should
+ * always be larger than our output buffer.
+ */
+
+static uch *inbuf; /* input buffer */
+static uch *window; /* Sliding window buffer, (and final output buffer) */
+
+static unsigned insize; /* valid bytes in inbuf */
+static unsigned inptr; /* index of next byte to be processed in inbuf */
+static unsigned outcnt; /* bytes in output buffer */
+
+/* gzip flag byte */
+#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */
+#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */
+#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */
+#define ORIG_NAME 0x08 /* bit 3 set: original file name present */
+#define COMMENT 0x10 /* bit 4 set: file comment present */
+#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */
+#define RESERVED 0xC0 /* bit 6,7: reserved */
+
+#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf())
+
+/* Diagnostic functions */
+#ifdef DEBUG
+# define Assert(cond,msg) {if(!(cond)) error(msg);}
+# define Trace(x) fprintf x
+# define Tracev(x) {if (verbose) fprintf x ;}
+# define Tracevv(x) {if (verbose>1) fprintf x ;}
+# define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
+# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
+#else
+# define Assert(cond,msg)
+# define Trace(x)
+# define Tracev(x)
+# define Tracevv(x)
+# define Tracec(c,x)
+# define Tracecv(c,x)
+#endif
+
+static int fill_inbuf(void);
+static void flush_window(void);
+static void error(char *m);
+static void gzip_mark(void **);
+static void gzip_release(void **);
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+static unsigned char *real_mode; /* Pointer to real-mode data */
+
+#define RM_EXT_MEM_K (*(unsigned short *)(real_mode + 0x2))
+#ifndef STANDARD_MEMORY_BIOS_CALL
+#define RM_ALT_MEM_K (*(unsigned long *)(real_mode + 0x1e0))
+#endif
+#define RM_SCREEN_INFO (*(struct screen_info *)(real_mode+0))
+
+extern unsigned char input_data[];
+extern int input_len;
+
+static long bytes_out = 0;
+
+static void *malloc(int size);
+static void free(void *where);
+
+static void *memset(void *s, int c, unsigned n);
+static void *memcpy(void *dest, const void *src, unsigned n);
+
+static void putstr(const char *);
+
+static long free_mem_ptr;
+static long free_mem_end_ptr;
+
+#define HEAP_SIZE 0x7000
+
+static char *vidmem = (char *)0xb8000;
+static int vidport;
+static int lines, cols;
+
+#include "../../../../lib/inflate.c"
+
+static void *malloc(int size)
+{
+ void *p;
+
+ if (size <0) error("Malloc error");
+ if (free_mem_ptr <= 0) error("Memory error");
+
+ free_mem_ptr = (free_mem_ptr + 3) & ~3; /* Align */
+
+ p = (void *)free_mem_ptr;
+ free_mem_ptr += size;
+
+ if (free_mem_ptr >= free_mem_end_ptr)
+ error("Out of memory");
+
+ return p;
+}
+
+static void free(void *where)
+{ /* Don't care */
+}
+
+static void gzip_mark(void **ptr)
+{
+ *ptr = (void *) free_mem_ptr;
+}
+
+static void gzip_release(void **ptr)
+{
+ free_mem_ptr = (long) *ptr;
+}
+
+static void scroll(void)
+{
+ int i;
+
+ memcpy ( vidmem, vidmem + cols * 2, ( lines - 1 ) * cols * 2 );
+ for ( i = ( lines - 1 ) * cols * 2; i < lines * cols * 2; i += 2 )
+ vidmem[i] = ' ';
+}
+
+static void putstr(const char *s)
+{
+ int x,y,pos;
+ char c;
+
+ x = RM_SCREEN_INFO.orig_x;
+ y = RM_SCREEN_INFO.orig_y;
+
+ while ( ( c = *s++ ) != '\0' ) {
+ if ( c == '\n' ) {
+ x = 0;
+ if ( ++y >= lines ) {
+ scroll();
+ y--;
+ }
+ } else {
+ vidmem [ ( x + cols * y ) * 2 ] = c;
+ if ( ++x >= cols ) {
+ x = 0;
+ if ( ++y >= lines ) {
+ scroll();
+ y--;
+ }
+ }
+ }
+ }
+
+ RM_SCREEN_INFO.orig_x = x;
+ RM_SCREEN_INFO.orig_y = y;
+
+ pos = (x + cols * y) * 2; /* Update cursor position */
+ outb_p(14, vidport);
+ outb_p(0xff & (pos >> 9), vidport+1);
+ outb_p(15, vidport);
+ outb_p(0xff & (pos >> 1), vidport+1);
+}
+
+static void* memset(void* s, int c, unsigned n)
+{
+ int i;
+ char *ss = (char*)s;
+
+ for (i=0;i> 8);
+ }
+ crc = c;
+ bytes_out += (ulg)outcnt;
+ outcnt = 0;
+}
+
+static void error(char *x)
+{
+ putstr("\n\n");
+ putstr(x);
+ putstr("\n\n -- System halted");
+
+ while(1); /* Halt */
+}
+
+asmlinkage void decompress_kernel(void *rmode, unsigned long heap,
+ uch *input_data, unsigned long input_len, uch *output)
+{
+ real_mode = rmode;
+
+ if (RM_SCREEN_INFO.orig_video_mode == 7) {
+ vidmem = (char *) 0xb0000;
+ vidport = 0x3b4;
+ } else {
+ vidmem = (char *) 0xb8000;
+ vidport = 0x3d4;
+ }
+
+ lines = RM_SCREEN_INFO.orig_video_lines;
+ cols = RM_SCREEN_INFO.orig_video_cols;
+
+ window = output; /* Output buffer (Normally at 1M) */
+ free_mem_ptr = heap; /* Heap */
+ free_mem_end_ptr = heap + HEAP_SIZE;
+ inbuf = input_data; /* Input buffer */
+ insize = input_len;
+ inptr = 0;
+
+ if ((ulg)output & (__KERNEL_ALIGN - 1))
+ error("Destination address not 2M aligned");
+ if ((ulg)output >= 0xffffffffffUL)
+ error("Destination address too large");
+
+ makecrc();
+ putstr(".\nDecompressing Linux...");
+ gunzip();
+ putstr("done.\nBooting the kernel.\n");
+ return;
+}
diff --git a/trunk/arch/x86/boot/compressed/relocs.c b/trunk/arch/x86/boot/compressed/relocs.c
index d01ea42187e6..7a0d00b2cf28 100644
--- a/trunk/arch/x86/boot/compressed/relocs.c
+++ b/trunk/arch/x86/boot/compressed/relocs.c
@@ -27,6 +27,11 @@ static unsigned long *relocs;
* absolute relocations present w.r.t these symbols.
*/
static const char* safe_abs_relocs[] = {
+ "__kernel_vsyscall",
+ "__kernel_rt_sigreturn",
+ "__kernel_sigreturn",
+ "SYSENTER_RETURN",
+ "VDSO_NOTE_MASK",
"xen_irq_disable_direct_reloc",
"xen_save_fl_direct_reloc",
};
@@ -40,8 +45,6 @@ static int is_safe_abs_reloc(const char* sym_name)
/* Match found */
return 1;
}
- if (strncmp(sym_name, "VDSO", 4) == 0)
- return 1;
if (strncmp(sym_name, "__crc_", 6) == 0)
return 1;
return 0;
diff --git a/trunk/arch/x86/boot/compressed/vmlinux_32.lds b/trunk/arch/x86/boot/compressed/vmlinux_32.lds
index bb3c48379c40..cc4854f6c6c1 100644
--- a/trunk/arch/x86/boot/compressed/vmlinux_32.lds
+++ b/trunk/arch/x86/boot/compressed/vmlinux_32.lds
@@ -3,17 +3,17 @@ OUTPUT_ARCH(i386)
ENTRY(startup_32)
SECTIONS
{
- /* Be careful parts of head_32.S assume startup_32 is at
- * address 0.
+ /* Be careful parts of head.S assume startup_32 is at
+ * address 0.
*/
- . = 0;
+ . = 0 ;
.text.head : {
_head = . ;
*(.text.head)
_ehead = . ;
}
- .rodata.compressed : {
- *(.rodata.compressed)
+ .data.compressed : {
+ *(.data.compressed)
}
.text : {
_text = .; /* Text */
diff --git a/trunk/arch/x86/boot/compressed/vmlinux_32.scr b/trunk/arch/x86/boot/compressed/vmlinux_32.scr
new file mode 100644
index 000000000000..707a88f7f29e
--- /dev/null
+++ b/trunk/arch/x86/boot/compressed/vmlinux_32.scr
@@ -0,0 +1,10 @@
+SECTIONS
+{
+ .data.compressed : {
+ input_len = .;
+ LONG(input_data_end - input_data) input_data = .;
+ *(.data)
+ output_len = . - 4;
+ input_data_end = .;
+ }
+}
diff --git a/trunk/arch/x86/boot/compressed/vmlinux_64.lds b/trunk/arch/x86/boot/compressed/vmlinux_64.lds
index f6e5b445f457..94c13e557fb4 100644
--- a/trunk/arch/x86/boot/compressed/vmlinux_64.lds
+++ b/trunk/arch/x86/boot/compressed/vmlinux_64.lds
@@ -3,19 +3,15 @@ OUTPUT_ARCH(i386:x86-64)
ENTRY(startup_64)
SECTIONS
{
- /* Be careful parts of head_64.S assume startup_64 is at
- * address 0.
+ /* Be careful parts of head.S assume startup_32 is at
+ * address 0.
*/
. = 0;
- .text.head : {
+ .text : {
_head = . ;
*(.text.head)
_ehead = . ;
- }
- .rodata.compressed : {
- *(.rodata.compressed)
- }
- .text : {
+ *(.text.compressed)
_text = .; /* Text */
*(.text)
*(.text.*)
diff --git a/trunk/arch/x86/boot/compressed/vmlinux.scr b/trunk/arch/x86/boot/compressed/vmlinux_64.scr
similarity index 84%
rename from trunk/arch/x86/boot/compressed/vmlinux.scr
rename to trunk/arch/x86/boot/compressed/vmlinux_64.scr
index f02382ae5c48..bd1429ce193e 100644
--- a/trunk/arch/x86/boot/compressed/vmlinux.scr
+++ b/trunk/arch/x86/boot/compressed/vmlinux_64.scr
@@ -1,6 +1,6 @@
SECTIONS
{
- .rodata.compressed : {
+ .text.compressed : {
input_len = .;
LONG(input_data_end - input_data) input_data = .;
*(.data)
diff --git a/trunk/arch/x86/boot/edd.c b/trunk/arch/x86/boot/edd.c
index 8721dc46a0b6..bd138e442ec2 100644
--- a/trunk/arch/x86/boot/edd.c
+++ b/trunk/arch/x86/boot/edd.c
@@ -129,7 +129,6 @@ void query_edd(void)
char eddarg[8];
int do_mbr = 1;
int do_edd = 1;
- int be_quiet;
int devno;
struct edd_info ei, *edp;
u32 *mbrptr;
@@ -141,21 +140,12 @@ void query_edd(void)
do_edd = 0;
}
- be_quiet = cmdline_find_option_bool("quiet");
-
edp = boot_params.eddbuf;
mbrptr = boot_params.edd_mbr_sig_buffer;
if (!do_edd)
return;
- /* Bugs in OnBoard or AddOnCards Bios may hang the EDD probe,
- * so give a hint if this happens.
- */
-
- if (!be_quiet)
- printf("Probing EDD (edd=off to disable)... ");
-
for (devno = 0x80; devno < 0x80+EDD_MBR_SIG_MAX; devno++) {
/*
* Scan the BIOS-supported hard disks and query EDD
@@ -172,9 +162,6 @@ void query_edd(void)
if (do_mbr && !read_mbr_sig(devno, &ei, mbrptr++))
boot_params.edd_mbr_sig_buf_entries = devno-0x80+1;
}
-
- if (!be_quiet)
- printf("ok\n");
}
#endif
diff --git a/trunk/arch/x86/boot/header.S b/trunk/arch/x86/boot/header.S
index 64ad9016585a..4cc5b0411db5 100644
--- a/trunk/arch/x86/boot/header.S
+++ b/trunk/arch/x86/boot/header.S
@@ -195,13 +195,10 @@ cmd_line_ptr: .long 0 # (Header version 0x0202 or later)
# can be located anywhere in
# low memory 0x10000 or higher.
-ramdisk_max: .long 0x7fffffff
+ramdisk_max: .long (-__PAGE_OFFSET-(512 << 20)-1) & 0x7fffffff
# (Header version 0x0203 or later)
# The highest safe address for
# the contents of an initrd
- # The current kernel allows up to 4 GB,
- # but leave it at 2 GB to avoid
- # possible bootloader bugs.
kernel_alignment: .long CONFIG_PHYSICAL_ALIGN #physical addr alignment
#required for protected mode
diff --git a/trunk/arch/x86/boot/main.c b/trunk/arch/x86/boot/main.c
index 7828da5cfd07..1f95750ede28 100644
--- a/trunk/arch/x86/boot/main.c
+++ b/trunk/arch/x86/boot/main.c
@@ -100,32 +100,20 @@ static void set_bios_mode(void)
#endif
}
-static void init_heap(void)
+void main(void)
{
- char *stack_end;
+ /* First, copy the boot header into the "zeropage" */
+ copy_boot_params();
+ /* End of heap check */
if (boot_params.hdr.loadflags & CAN_USE_HEAP) {
- asm("leal %P1(%%esp),%0"
- : "=r" (stack_end) : "i" (-STACK_SIZE));
-
- heap_end = (char *)
- ((size_t)boot_params.hdr.heap_end_ptr + 0x200);
- if (heap_end > stack_end)
- heap_end = stack_end;
+ heap_end = (char *)(boot_params.hdr.heap_end_ptr
+ +0x200-STACK_SIZE);
} else {
/* Boot protocol 2.00 only, no heap available */
puts("WARNING: Ancient bootloader, some functionality "
"may be limited!\n");
}
-}
-
-void main(void)
-{
- /* First, copy the boot header into the "zeropage" */
- copy_boot_params();
-
- /* End of heap check */
- init_heap();
/* Make sure we have all the proper CPU support */
if (validate_cpu()) {
@@ -143,6 +131,9 @@ void main(void)
/* Set keyboard repeat rate (why?) */
keyboard_set_repeat();
+ /* Set the video mode */
+ set_video();
+
/* Query MCA information */
query_mca();
@@ -163,10 +154,6 @@ void main(void)
#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
query_edd();
#endif
-
- /* Set the video mode */
- set_video();
-
/* Do the last things and invoke protected mode */
go_to_protected_mode();
}
diff --git a/trunk/arch/x86/boot/pm.c b/trunk/arch/x86/boot/pm.c
index 1a0f936c160b..09fb342cc62e 100644
--- a/trunk/arch/x86/boot/pm.c
+++ b/trunk/arch/x86/boot/pm.c
@@ -104,7 +104,7 @@ static void reset_coprocessor(void)
(((u64)(base & 0xff000000) << 32) | \
((u64)flags << 40) | \
((u64)(limit & 0x00ff0000) << 32) | \
- ((u64)(base & 0x00ffffff) << 16) | \
+ ((u64)(base & 0x00ffff00) << 16) | \
((u64)(limit & 0x0000ffff)))
struct gdt_ptr {
@@ -121,10 +121,6 @@ static void setup_gdt(void)
[GDT_ENTRY_BOOT_CS] = GDT_ENTRY(0xc09b, 0, 0xfffff),
/* DS: data, read/write, 4 GB, base 0 */
[GDT_ENTRY_BOOT_DS] = GDT_ENTRY(0xc093, 0, 0xfffff),
- /* TSS: 32-bit tss, 104 bytes, base 4096 */
- /* We only have a TSS here to keep Intel VT happy;
- we don't actually use it for anything. */
- [GDT_ENTRY_BOOT_TSS] = GDT_ENTRY(0x0089, 4096, 103),
};
/* Xen HVM incorrectly stores a pointer to the gdt_ptr, instead
of the gdt_ptr contents. Thus, make it static so it will
diff --git a/trunk/arch/x86/boot/pmjump.S b/trunk/arch/x86/boot/pmjump.S
index f5402d51f7c3..fa6bed1fac14 100644
--- a/trunk/arch/x86/boot/pmjump.S
+++ b/trunk/arch/x86/boot/pmjump.S
@@ -15,7 +15,6 @@
*/
#include
-#include
#include
.text
@@ -30,55 +29,28 @@
*/
protected_mode_jump:
movl %edx, %esi # Pointer to boot_params table
-
- xorl %ebx, %ebx
- movw %cs, %bx
- shll $4, %ebx
- addl %ebx, 2f
+ movl %eax, 2f # Patch ljmpl instruction
movw $__BOOT_DS, %cx
- movw $__BOOT_TSS, %di
+ xorl %ebx, %ebx # Per the 32-bit boot protocol
+ xorl %ebp, %ebp # Per the 32-bit boot protocol
+ xorl %edi, %edi # Per the 32-bit boot protocol
movl %cr0, %edx
- orb $X86_CR0_PE, %dl # Protected mode
+ orb $1, %dl # Protected mode (PE) bit
movl %edx, %cr0
jmp 1f # Short jump to serialize on 386/486
1:
- # Transition to 32-bit mode
+ movw %cx, %ds
+ movw %cx, %es
+ movw %cx, %fs
+ movw %cx, %gs
+ movw %cx, %ss
+
+ # Jump to the 32-bit entrypoint
.byte 0x66, 0xea # ljmpl opcode
-2: .long in_pm32 # offset
+2: .long 0 # offset
.word __BOOT_CS # segment
.size protected_mode_jump, .-protected_mode_jump
-
- .code32
- .type in_pm32, @function
-in_pm32:
- # Set up data segments for flat 32-bit mode
- movl %ecx, %ds
- movl %ecx, %es
- movl %ecx, %fs
- movl %ecx, %gs
- movl %ecx, %ss
- # The 32-bit code sets up its own stack, but this way we do have
- # a valid stack if some debugging hack wants to use it.
- addl %ebx, %esp
-
- # Set up TR to make Intel VT happy
- ltr %di
-
- # Clear registers to allow for future extensions to the
- # 32-bit boot protocol
- xorl %ecx, %ecx
- xorl %edx, %edx
- xorl %ebx, %ebx
- xorl %ebp, %ebp
- xorl %edi, %edi
-
- # Set up LDTR to make Intel VT happy
- lldt %cx
-
- jmpl *%eax # Jump to the 32-bit entrypoint
-
- .size in_pm32, .-in_pm32
diff --git a/trunk/arch/x86/boot/video-bios.c b/trunk/arch/x86/boot/video-bios.c
index ff664a117096..ed0672a81870 100644
--- a/trunk/arch/x86/boot/video-bios.c
+++ b/trunk/arch/x86/boot/video-bios.c
@@ -104,7 +104,6 @@ static int bios_probe(void)
mi = GET_HEAP(struct mode_info, 1);
mi->mode = VIDEO_FIRST_BIOS+mode;
- mi->depth = 0; /* text */
mi->x = rdfs16(0x44a);
mi->y = rdfs8(0x484)+1;
nmodes++;
@@ -117,7 +116,7 @@ static int bios_probe(void)
__videocard video_bios =
{
- .card_name = "BIOS",
+ .card_name = "BIOS (scanned)",
.probe = bios_probe,
.set_mode = bios_set_mode,
.unsafe = 1,
diff --git a/trunk/arch/x86/boot/video-vesa.c b/trunk/arch/x86/boot/video-vesa.c
index 662dd2f13068..4716b9a96357 100644
--- a/trunk/arch/x86/boot/video-vesa.c
+++ b/trunk/arch/x86/boot/video-vesa.c
@@ -79,28 +79,20 @@ static int vesa_probe(void)
/* Text Mode, TTY BIOS supported,
supported by hardware */
mi = GET_HEAP(struct mode_info, 1);
- mi->mode = mode + VIDEO_FIRST_VESA;
- mi->depth = 0; /* text */
- mi->x = vminfo.h_res;
- mi->y = vminfo.v_res;
+ mi->mode = mode + VIDEO_FIRST_VESA;
+ mi->x = vminfo.h_res;
+ mi->y = vminfo.v_res;
nmodes++;
- } else if ((vminfo.mode_attr & 0x99) == 0x99 &&
- (vminfo.memory_layout == 4 ||
- vminfo.memory_layout == 6) &&
- vminfo.memory_planes == 1) {
+ } else if ((vminfo.mode_attr & 0x99) == 0x99) {
#ifdef CONFIG_FB
/* Graphics mode, color, linear frame buffer
- supported. Only register the mode if
- if framebuffer is configured, however,
- otherwise the user will be left without a screen.
- We don't require CONFIG_FB_VESA, however, since
- some of the other framebuffer drivers can use
- this mode-setting, too. */
+ supported -- register the mode but hide from
+ the menu. Only do this if framebuffer is
+ configured, however, otherwise the user will
+ be left without a screen. */
mi = GET_HEAP(struct mode_info, 1);
mi->mode = mode + VIDEO_FIRST_VESA;
- mi->depth = vminfo.bpp;
- mi->x = vminfo.h_res;
- mi->y = vminfo.v_res;
+ mi->x = mi->y = 0;
nmodes++;
#endif
}
diff --git a/trunk/arch/x86/boot/video-vga.c b/trunk/arch/x86/boot/video-vga.c
index 7259387b7d19..aef02f9ec0c1 100644
--- a/trunk/arch/x86/boot/video-vga.c
+++ b/trunk/arch/x86/boot/video-vga.c
@@ -18,22 +18,22 @@
#include "video.h"
static struct mode_info vga_modes[] = {
- { VIDEO_80x25, 80, 25, 0 },
- { VIDEO_8POINT, 80, 50, 0 },
- { VIDEO_80x43, 80, 43, 0 },
- { VIDEO_80x28, 80, 28, 0 },
- { VIDEO_80x30, 80, 30, 0 },
- { VIDEO_80x34, 80, 34, 0 },
- { VIDEO_80x60, 80, 60, 0 },
+ { VIDEO_80x25, 80, 25 },
+ { VIDEO_8POINT, 80, 50 },
+ { VIDEO_80x43, 80, 43 },
+ { VIDEO_80x28, 80, 28 },
+ { VIDEO_80x30, 80, 30 },
+ { VIDEO_80x34, 80, 34 },
+ { VIDEO_80x60, 80, 60 },
};
static struct mode_info ega_modes[] = {
- { VIDEO_80x25, 80, 25, 0 },
- { VIDEO_8POINT, 80, 43, 0 },
+ { VIDEO_80x25, 80, 25 },
+ { VIDEO_8POINT, 80, 43 },
};
static struct mode_info cga_modes[] = {
- { VIDEO_80x25, 80, 25, 0 },
+ { VIDEO_80x25, 80, 25 },
};
__videocard video_vga;
diff --git a/trunk/arch/x86/boot/video.c b/trunk/arch/x86/boot/video.c
index 696d08f3843c..ad9712f01739 100644
--- a/trunk/arch/x86/boot/video.c
+++ b/trunk/arch/x86/boot/video.c
@@ -293,28 +293,13 @@ static void display_menu(void)
struct mode_info *mi;
char ch;
int i;
- int nmodes;
- int modes_per_line;
- int col;
- nmodes = 0;
- for (card = video_cards; card < video_cards_end; card++)
- nmodes += card->nmodes;
+ puts("Mode: COLSxROWS:\n");
- modes_per_line = 1;
- if (nmodes >= 20)
- modes_per_line = 3;
-
- for (col = 0; col < modes_per_line; col++)
- puts("Mode: Resolution: Type: ");
- putchar('\n');
-
- col = 0;
ch = '0';
for (card = video_cards; card < video_cards_end; card++) {
mi = card->modes;
for (i = 0; i < card->nmodes; i++, mi++) {
- char resbuf[32];
int visible = mi->x && mi->y;
u16 mode_id = mi->mode ? mi->mode :
(mi->y << 8)+mi->x;
@@ -322,18 +307,8 @@ static void display_menu(void)
if (!visible)
continue; /* Hidden mode */
- if (mi->depth)
- sprintf(resbuf, "%dx%d", mi->y, mi->depth);
- else
- sprintf(resbuf, "%d", mi->y);
-
- printf("%c %03X %4dx%-7s %-6s",
- ch, mode_id, mi->x, resbuf, card->card_name);
- col++;
- if (col >= modes_per_line) {
- putchar('\n');
- col = 0;
- }
+ printf("%c %04X %3dx%-3d %s\n",
+ ch, mode_id, mi->x, mi->y, card->card_name);
if (ch == '9')
ch = 'a';
@@ -343,8 +318,6 @@ static void display_menu(void)
ch++;
}
}
- if (col)
- putchar('\n');
}
#define H(x) ((x)-'a'+10)
diff --git a/trunk/arch/x86/boot/video.h b/trunk/arch/x86/boot/video.h
index d69347f79e8e..b92447d51213 100644
--- a/trunk/arch/x86/boot/video.h
+++ b/trunk/arch/x86/boot/video.h
@@ -83,8 +83,7 @@ void store_screen(void);
struct mode_info {
u16 mode; /* Mode number (vga= style) */
- u16 x, y; /* Width, height */
- u16 depth; /* Bits per pixel, 0 for text mode */
+ u8 x, y; /* Width, height */
};
struct card_info {
diff --git a/trunk/arch/x86/boot/voyager.c b/trunk/arch/x86/boot/voyager.c
index 6499e3239b41..61c8fe0453be 100644
--- a/trunk/arch/x86/boot/voyager.c
+++ b/trunk/arch/x86/boot/voyager.c
@@ -16,6 +16,8 @@
#include "boot.h"
+#ifdef CONFIG_X86_VOYAGER
+
int query_voyager(void)
{
u8 err;
@@ -40,3 +42,5 @@ int query_voyager(void)
copy_from_fs(data_ptr, di, 7); /* Table is 7 bytes apparently */
return 0;
}
+
+#endif /* CONFIG_X86_VOYAGER */
diff --git a/trunk/arch/x86/configs/i386_defconfig b/trunk/arch/x86/configs/i386_defconfig
index 77562e7cdab6..54ee1764fdae 100644
--- a/trunk/arch/x86/configs/i386_defconfig
+++ b/trunk/arch/x86/configs/i386_defconfig
@@ -99,9 +99,9 @@ CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_AS=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_IOSCHED_CFQ=y
-# CONFIG_DEFAULT_AS is not set
+CONFIG_DEFAULT_AS=y
# CONFIG_DEFAULT_DEADLINE is not set
-CONFIG_DEFAULT_CFQ=y
+# CONFIG_DEFAULT_CFQ is not set
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="anticipatory"
diff --git a/trunk/arch/x86/configs/x86_64_defconfig b/trunk/arch/x86/configs/x86_64_defconfig
index 9e2b0ef851de..38a83f9c966f 100644
--- a/trunk/arch/x86/configs/x86_64_defconfig
+++ b/trunk/arch/x86/configs/x86_64_defconfig
@@ -145,6 +145,15 @@ CONFIG_K8_NUMA=y
CONFIG_NODES_SHIFT=6
CONFIG_X86_64_ACPI_NUMA=y
CONFIG_NUMA_EMU=y
+CONFIG_ARCH_DISCONTIGMEM_ENABLE=y
+CONFIG_ARCH_DISCONTIGMEM_DEFAULT=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_SELECT_MEMORY_MODEL=y
+# CONFIG_FLATMEM_MANUAL is not set
+CONFIG_DISCONTIGMEM_MANUAL=y
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_DISCONTIGMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
CONFIG_NEED_MULTIPLE_NODES=y
# CONFIG_SPARSEMEM_STATIC is not set
CONFIG_SPLIT_PTLOCK_CPUS=4
diff --git a/trunk/arch/x86/ia32/Makefile b/trunk/arch/x86/ia32/Makefile
index 52d0ccfcf6ea..e2edda255a84 100644
--- a/trunk/arch/x86/ia32/Makefile
+++ b/trunk/arch/x86/ia32/Makefile
@@ -2,7 +2,9 @@
# Makefile for the ia32 kernel emulation subsystem.
#
-obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o
+obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o tls32.o \
+ ia32_binfmt.o fpu32.o ptrace32.o syscall32.o syscall32_syscall.o \
+ mmap32.o
sysv-$(CONFIG_SYSVIPC) := ipc32.o
obj-$(CONFIG_IA32_EMULATION) += $(sysv-y)
@@ -11,3 +13,40 @@ obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
audit-class-$(CONFIG_AUDIT) := audit.o
obj-$(CONFIG_IA32_EMULATION) += $(audit-class-y)
+
+$(obj)/syscall32_syscall.o: \
+ $(foreach F,sysenter syscall,$(obj)/vsyscall-$F.so)
+
+# Teach kbuild about targets
+targets := $(foreach F,$(addprefix vsyscall-,sysenter syscall),\
+ $F.o $F.so $F.so.dbg)
+
+# The DSO images are built using a special linker script
+quiet_cmd_syscall = SYSCALL $@
+ cmd_syscall = $(CC) -m32 -nostdlib -shared \
+ $(call ld-option, -Wl$(comma)--hash-style=sysv) \
+ -Wl,-soname=linux-gate.so.1 -o $@ \
+ -Wl,-T,$(filter-out FORCE,$^)
+
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+ $(call if_changed,objcopy)
+
+$(obj)/vsyscall-sysenter.so.dbg $(obj)/vsyscall-syscall.so.dbg: \
+$(obj)/vsyscall-%.so.dbg: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
+ $(call if_changed,syscall)
+
+AFLAGS_vsyscall-sysenter.o = -m32 -Wa,-32
+AFLAGS_vsyscall-syscall.o = -m32 -Wa,-32
+
+vdsos := vdso32-sysenter.so vdso32-syscall.so
+
+quiet_cmd_vdso_install = INSTALL $@
+ cmd_vdso_install = cp $(@:vdso32-%.so=$(obj)/vsyscall-%.so.dbg) \
+ $(MODLIB)/vdso/$@
+
+$(vdsos):
+ @mkdir -p $(MODLIB)/vdso
+ $(call cmd,vdso_install)
+
+vdso_install: $(vdsos)
diff --git a/trunk/arch/x86/ia32/audit.c b/trunk/arch/x86/ia32/audit.c
index 5d7b381da692..91b7b5922dfa 100644
--- a/trunk/arch/x86/ia32/audit.c
+++ b/trunk/arch/x86/ia32/audit.c
@@ -27,7 +27,7 @@ unsigned ia32_signal_class[] = {
int ia32_classify_syscall(unsigned syscall)
{
- switch (syscall) {
+ switch(syscall) {
case __NR_open:
return 2;
case __NR_openat:
diff --git a/trunk/arch/x86/ia32/fpu32.c b/trunk/arch/x86/ia32/fpu32.c
new file mode 100644
index 000000000000..2c8209a3605a
--- /dev/null
+++ b/trunk/arch/x86/ia32/fpu32.c
@@ -0,0 +1,183 @@
+/*
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ * FXSAVE<->i387 conversion support. Based on code by Gareth Hughes.
+ * This is used for ptrace, signals and coredumps in 32bit emulation.
+ */
+
+#include
+#include
+#include
+#include
+#include
+
+static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
+{
+ unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+ /* Transform each pair of bits into 01 (valid) or 00 (empty) */
+ tmp = ~twd;
+ tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+ /* and move the valid bits to the lower byte. */
+ tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+ tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+ tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+ return tmp;
+}
+
+static inline unsigned long twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
+{
+ struct _fpxreg *st = NULL;
+ unsigned long tos = (fxsave->swd >> 11) & 7;
+ unsigned long twd = (unsigned long) fxsave->twd;
+ unsigned long tag;
+ unsigned long ret = 0xffff0000;
+ int i;
+
+#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16);
+
+ for (i = 0 ; i < 8 ; i++) {
+ if (twd & 0x1) {
+ st = FPREG_ADDR( fxsave, (i - tos) & 7 );
+
+ switch (st->exponent & 0x7fff) {
+ case 0x7fff:
+ tag = 2; /* Special */
+ break;
+ case 0x0000:
+ if ( !st->significand[0] &&
+ !st->significand[1] &&
+ !st->significand[2] &&
+ !st->significand[3] ) {
+ tag = 1; /* Zero */
+ } else {
+ tag = 2; /* Special */
+ }
+ break;
+ default:
+ if (st->significand[3] & 0x8000) {
+ tag = 0; /* Valid */
+ } else {
+ tag = 2; /* Special */
+ }
+ break;
+ }
+ } else {
+ tag = 3; /* Empty */
+ }
+ ret |= (tag << (2 * i));
+ twd = twd >> 1;
+ }
+ return ret;
+}
+
+
+static inline int convert_fxsr_from_user(struct i387_fxsave_struct *fxsave,
+ struct _fpstate_ia32 __user *buf)
+{
+ struct _fpxreg *to;
+ struct _fpreg __user *from;
+ int i;
+ u32 v;
+ int err = 0;
+
+#define G(num,val) err |= __get_user(val, num + (u32 __user *)buf)
+ G(0, fxsave->cwd);
+ G(1, fxsave->swd);
+ G(2, fxsave->twd);
+ fxsave->twd = twd_i387_to_fxsr(fxsave->twd);
+ G(3, fxsave->rip);
+ G(4, v);
+ fxsave->fop = v>>16; /* cs ignored */
+ G(5, fxsave->rdp);
+ /* 6: ds ignored */
+#undef G
+ if (err)
+ return -1;
+
+ to = (struct _fpxreg *)&fxsave->st_space[0];
+ from = &buf->_st[0];
+ for (i = 0 ; i < 8 ; i++, to++, from++) {
+ if (__copy_from_user(to, from, sizeof(*from)))
+ return -1;
+ }
+ return 0;
+}
+
+
+static inline int convert_fxsr_to_user(struct _fpstate_ia32 __user *buf,
+ struct i387_fxsave_struct *fxsave,
+ struct pt_regs *regs,
+ struct task_struct *tsk)
+{
+ struct _fpreg __user *to;
+ struct _fpxreg *from;
+ int i;
+ u16 cs,ds;
+ int err = 0;
+
+ if (tsk == current) {
+ /* should be actually ds/cs at fpu exception time,
+ but that information is not available in 64bit mode. */
+ asm("movw %%ds,%0 " : "=r" (ds));
+ asm("movw %%cs,%0 " : "=r" (cs));
+ } else { /* ptrace. task has stopped. */
+ ds = tsk->thread.ds;
+ cs = regs->cs;
+ }
+
+#define P(num,val) err |= __put_user(val, num + (u32 __user *)buf)
+ P(0, (u32)fxsave->cwd | 0xffff0000);
+ P(1, (u32)fxsave->swd | 0xffff0000);
+ P(2, twd_fxsr_to_i387(fxsave));
+ P(3, (u32)fxsave->rip);
+ P(4, cs | ((u32)fxsave->fop) << 16);
+ P(5, fxsave->rdp);
+ P(6, 0xffff0000 | ds);
+#undef P
+
+ if (err)
+ return -1;
+
+ to = &buf->_st[0];
+ from = (struct _fpxreg *) &fxsave->st_space[0];
+ for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
+ if (__copy_to_user(to, from, sizeof(*to)))
+ return -1;
+ }
+ return 0;
+}
+
+int restore_i387_ia32(struct task_struct *tsk, struct _fpstate_ia32 __user *buf, int fsave)
+{
+ clear_fpu(tsk);
+ if (!fsave) {
+ if (__copy_from_user(&tsk->thread.i387.fxsave,
+ &buf->_fxsr_env[0],
+ sizeof(struct i387_fxsave_struct)))
+ return -1;
+ tsk->thread.i387.fxsave.mxcsr &= mxcsr_feature_mask;
+ set_stopped_child_used_math(tsk);
+ }
+ return convert_fxsr_from_user(&tsk->thread.i387.fxsave, buf);
+}
+
+int save_i387_ia32(struct task_struct *tsk,
+ struct _fpstate_ia32 __user *buf,
+ struct pt_regs *regs,
+ int fsave)
+{
+ int err = 0;
+
+ init_fpu(tsk);
+ if (convert_fxsr_to_user(buf, &tsk->thread.i387.fxsave, regs, tsk))
+ return -1;
+ if (fsave)
+ return 0;
+ err |= __put_user(tsk->thread.i387.fxsave.swd, &buf->status);
+ if (fsave)
+ return err ? -1 : 1;
+ err |= __put_user(X86_FXSR_MAGIC, &buf->magic);
+ err |= __copy_to_user(&buf->_fxsr_env[0], &tsk->thread.i387.fxsave,
+ sizeof(struct i387_fxsave_struct));
+ return err ? -1 : 1;
+}
diff --git a/trunk/arch/x86/ia32/ia32_aout.c b/trunk/arch/x86/ia32/ia32_aout.c
index e4c12079171b..f82e1a94fcb7 100644
--- a/trunk/arch/x86/ia32/ia32_aout.c
+++ b/trunk/arch/x86/ia32/ia32_aout.c
@@ -25,7 +25,6 @@
#include
#include
#include
-#include
#include
#include
@@ -37,67 +36,61 @@
#undef WARN_OLD
#undef CORE_DUMP /* probably broken */
-static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs);
-static int load_aout_library(struct file *);
+static int load_aout_binary(struct linux_binprm *, struct pt_regs * regs);
+static int load_aout_library(struct file*);
#ifdef CORE_DUMP
-static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
- unsigned long limit);
+static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit);
/*
* fill in the user structure for a core dump..
*/
-static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
+static void dump_thread32(struct pt_regs * regs, struct user32 * dump)
{
- u32 fs, gs;
+ u32 fs,gs;
/* changed the size calculations - should hopefully work better. lbt */
dump->magic = CMAGIC;
dump->start_code = 0;
- dump->start_stack = regs->sp & ~(PAGE_SIZE - 1);
+ dump->start_stack = regs->rsp & ~(PAGE_SIZE - 1);
dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
- dump->u_dsize = ((unsigned long)
- (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
+ dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
dump->u_dsize -= dump->u_tsize;
dump->u_ssize = 0;
- dump->u_debugreg[0] = current->thread.debugreg0;
- dump->u_debugreg[1] = current->thread.debugreg1;
- dump->u_debugreg[2] = current->thread.debugreg2;
- dump->u_debugreg[3] = current->thread.debugreg3;
- dump->u_debugreg[4] = 0;
- dump->u_debugreg[5] = 0;
- dump->u_debugreg[6] = current->thread.debugreg6;
- dump->u_debugreg[7] = current->thread.debugreg7;
-
- if (dump->start_stack < 0xc0000000) {
- unsigned long tmp;
-
- tmp = (unsigned long) (0xc0000000 - dump->start_stack);
- dump->u_ssize = tmp >> PAGE_SHIFT;
- }
-
- dump->regs.bx = regs->bx;
- dump->regs.cx = regs->cx;
- dump->regs.dx = regs->dx;
- dump->regs.si = regs->si;
- dump->regs.di = regs->di;
- dump->regs.bp = regs->bp;
- dump->regs.ax = regs->ax;
+ dump->u_debugreg[0] = current->thread.debugreg0;
+ dump->u_debugreg[1] = current->thread.debugreg1;
+ dump->u_debugreg[2] = current->thread.debugreg2;
+ dump->u_debugreg[3] = current->thread.debugreg3;
+ dump->u_debugreg[4] = 0;
+ dump->u_debugreg[5] = 0;
+ dump->u_debugreg[6] = current->thread.debugreg6;
+ dump->u_debugreg[7] = current->thread.debugreg7;
+
+ if (dump->start_stack < 0xc0000000)
+ dump->u_ssize = ((unsigned long) (0xc0000000 - dump->start_stack)) >> PAGE_SHIFT;
+
+ dump->regs.ebx = regs->rbx;
+ dump->regs.ecx = regs->rcx;
+ dump->regs.edx = regs->rdx;
+ dump->regs.esi = regs->rsi;
+ dump->regs.edi = regs->rdi;
+ dump->regs.ebp = regs->rbp;
+ dump->regs.eax = regs->rax;
dump->regs.ds = current->thread.ds;
dump->regs.es = current->thread.es;
asm("movl %%fs,%0" : "=r" (fs)); dump->regs.fs = fs;
- asm("movl %%gs,%0" : "=r" (gs)); dump->regs.gs = gs;
- dump->regs.orig_ax = regs->orig_ax;
- dump->regs.ip = regs->ip;
+ asm("movl %%gs,%0" : "=r" (gs)); dump->regs.gs = gs;
+ dump->regs.orig_eax = regs->orig_rax;
+ dump->regs.eip = regs->rip;
dump->regs.cs = regs->cs;
- dump->regs.flags = regs->flags;
- dump->regs.sp = regs->sp;
+ dump->regs.eflags = regs->eflags;
+ dump->regs.esp = regs->rsp;
dump->regs.ss = regs->ss;
#if 1 /* FIXME */
dump->u_fpvalid = 0;
#else
- dump->u_fpvalid = dump_fpu(regs, &dump->i387);
+ dump->u_fpvalid = dump_fpu (regs, &dump->i387);
#endif
}
@@ -135,19 +128,15 @@ static int dump_write(struct file *file, const void *addr, int nr)
return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
}
-#define DUMP_WRITE(addr, nr) \
+#define DUMP_WRITE(addr, nr) \
if (!dump_write(file, (void *)(addr), (nr))) \
goto end_coredump;
-#define DUMP_SEEK(offset) \
- if (file->f_op->llseek) { \
- if (file->f_op->llseek(file, (offset), 0) != (offset)) \
- goto end_coredump; \
- } else \
- file->f_pos = (offset)
-
-#define START_DATA() (u.u_tsize << PAGE_SHIFT)
-#define START_STACK(u) (u.start_stack)
+#define DUMP_SEEK(offset) \
+if (file->f_op->llseek) { \
+ if (file->f_op->llseek(file,(offset),0) != (offset)) \
+ goto end_coredump; \
+} else file->f_pos = (offset)
/*
* Routine writes a core dump image in the current directory.
@@ -159,70 +148,62 @@ static int dump_write(struct file *file, const void *addr, int nr)
* dumping of the process results in another error..
*/
-static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
- unsigned long limit)
+static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit)
{
mm_segment_t fs;
int has_dumped = 0;
unsigned long dump_start, dump_size;
struct user32 dump;
+# define START_DATA(u) (u.u_tsize << PAGE_SHIFT)
+# define START_STACK(u) (u.start_stack)
fs = get_fs();
set_fs(KERNEL_DS);
has_dumped = 1;
current->flags |= PF_DUMPCORE;
- strncpy(dump.u_comm, current->comm, sizeof(current->comm));
- dump.u_ar0 = (u32)(((unsigned long)(&dump.regs)) -
- ((unsigned long)(&dump)));
+ strncpy(dump.u_comm, current->comm, sizeof(current->comm));
+ dump.u_ar0 = (u32)(((unsigned long)(&dump.regs)) - ((unsigned long)(&dump)));
dump.signal = signr;
dump_thread32(regs, &dump);
- /*
- * If the size of the dump file exceeds the rlimit, then see
- * what would happen if we wrote the stack, but not the data
- * area.
- */
+/* If the size of the dump file exceeds the rlimit, then see what would happen
+ if we wrote the stack, but not the data area. */
if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > limit)
dump.u_dsize = 0;
- /* Make sure we have enough room to write the stack and data areas. */
+/* Make sure we have enough room to write the stack and data areas. */
if ((dump.u_ssize + 1) * PAGE_SIZE > limit)
dump.u_ssize = 0;
- /* make sure we actually have a data and stack area to dump */
+/* make sure we actually have a data and stack area to dump */
set_fs(USER_DS);
- if (!access_ok(VERIFY_READ, (void *) (unsigned long)START_DATA(dump),
- dump.u_dsize << PAGE_SHIFT))
+ if (!access_ok(VERIFY_READ, (void *) (unsigned long)START_DATA(dump), dump.u_dsize << PAGE_SHIFT))
dump.u_dsize = 0;
- if (!access_ok(VERIFY_READ, (void *) (unsigned long)START_STACK(dump),
- dump.u_ssize << PAGE_SHIFT))
+ if (!access_ok(VERIFY_READ, (void *) (unsigned long)START_STACK(dump), dump.u_ssize << PAGE_SHIFT))
dump.u_ssize = 0;
set_fs(KERNEL_DS);
- /* struct user */
- DUMP_WRITE(&dump, sizeof(dump));
- /* Now dump all of the user data. Include malloced stuff as well */
+/* struct user */
+ DUMP_WRITE(&dump,sizeof(dump));
+/* Now dump all of the user data. Include malloced stuff as well */
DUMP_SEEK(PAGE_SIZE);
- /* now we start writing out the user space info */
+/* now we start writing out the user space info */
set_fs(USER_DS);
- /* Dump the data area */
+/* Dump the data area */
if (dump.u_dsize != 0) {
dump_start = START_DATA(dump);
dump_size = dump.u_dsize << PAGE_SHIFT;
- DUMP_WRITE(dump_start, dump_size);
+ DUMP_WRITE(dump_start,dump_size);
}
- /* Now prepare to dump the stack area */
+/* Now prepare to dump the stack area */
if (dump.u_ssize != 0) {
dump_start = START_STACK(dump);
dump_size = dump.u_ssize << PAGE_SHIFT;
- DUMP_WRITE(dump_start, dump_size);
+ DUMP_WRITE(dump_start,dump_size);
}
- /*
- * Finally dump the task struct. Not be used by gdb, but
- * could be useful
- */
+/* Finally dump the task struct. Not be used by gdb, but could be useful */
set_fs(KERNEL_DS);
- DUMP_WRITE(current, sizeof(*current));
+ DUMP_WRITE(current,sizeof(*current));
end_coredump:
set_fs(fs);
return has_dumped;
@@ -236,34 +217,35 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
*/
static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm)
{
- u32 __user *argv, *envp, *sp;
- int argc = bprm->argc, envc = bprm->envc;
+ u32 __user *argv;
+ u32 __user *envp;
+ u32 __user *sp;
+ int argc = bprm->argc;
+ int envc = bprm->envc;
sp = (u32 __user *) ((-(unsigned long)sizeof(u32)) & (unsigned long) p);
sp -= envc+1;
envp = sp;
sp -= argc+1;
argv = sp;
- put_user((unsigned long) envp, --sp);
- put_user((unsigned long) argv, --sp);
- put_user(argc, --sp);
+ put_user((unsigned long) envp,--sp);
+ put_user((unsigned long) argv,--sp);
+ put_user(argc,--sp);
current->mm->arg_start = (unsigned long) p;
- while (argc-- > 0) {
+ while (argc-->0) {
char c;
-
- put_user((u32)(unsigned long)p, argv++);
+ put_user((u32)(unsigned long)p,argv++);
do {
- get_user(c, p++);
+ get_user(c,p++);
} while (c);
}
put_user(0, argv);
current->mm->arg_end = current->mm->env_start = (unsigned long) p;
- while (envc-- > 0) {
+ while (envc-->0) {
char c;
-
- put_user((u32)(unsigned long)p, envp++);
+ put_user((u32)(unsigned long)p,envp++);
do {
- get_user(c, p++);
+ get_user(c,p++);
} while (c);
}
put_user(0, envp);
@@ -275,18 +257,20 @@ static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm)
* These are the functions used to load a.out style executables and shared
* libraries. There is no binary dependent code anywhere else.
*/
-static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
+
+static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
{
- unsigned long error, fd_offset, rlim;
struct exec ex;
+ unsigned long error;
+ unsigned long fd_offset;
+ unsigned long rlim;
int retval;
ex = *((struct exec *) bprm->buf); /* exec-header */
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
N_TRSIZE(ex) || N_DRSIZE(ex) ||
- i_size_read(bprm->file->f_path.dentry->d_inode) <
- ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
+ i_size_read(bprm->file->f_path.dentry->d_inode) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
return -ENOEXEC;
}
@@ -307,13 +291,13 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
if (retval)
return retval;
- regs->cs = __USER32_CS;
+ regs->cs = __USER32_CS;
regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
regs->r13 = regs->r14 = regs->r15 = 0;
/* OK, This is the point of no return */
set_personality(PER_LINUX);
- set_thread_flag(TIF_IA32);
+ set_thread_flag(TIF_IA32);
clear_thread_flag(TIF_ABI_PENDING);
current->mm->end_code = ex.a_text +
@@ -327,7 +311,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
current->mm->mmap = NULL;
compute_creds(bprm);
- current->flags &= ~PF_FORKNOEXEC;
+ current->flags &= ~PF_FORKNOEXEC;
if (N_MAGIC(ex) == OMAGIC) {
unsigned long text_addr, map_size;
@@ -354,31 +338,30 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
send_sig(SIGKILL, current, 0);
return error;
}
-
+
flush_icache_range(text_addr, text_addr+ex.a_text+ex.a_data);
} else {
#ifdef WARN_OLD
static unsigned long error_time, error_time2;
if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
- (N_MAGIC(ex) != NMAGIC) &&
- time_after(jiffies, error_time2 + 5*HZ)) {
+ (N_MAGIC(ex) != NMAGIC) && (jiffies-error_time2) > 5*HZ)
+ {
printk(KERN_NOTICE "executable not page aligned\n");
error_time2 = jiffies;
}
if ((fd_offset & ~PAGE_MASK) != 0 &&
- time_after(jiffies, error_time + 5*HZ)) {
- printk(KERN_WARNING
- "fd_offset is not page aligned. Please convert "
- "program: %s\n",
+ (jiffies-error_time) > 5*HZ)
+ {
+ printk(KERN_WARNING
+ "fd_offset is not page aligned. Please convert program: %s\n",
bprm->file->f_path.dentry->d_name.name);
error_time = jiffies;
}
#endif
- if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
+ if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
loff_t pos = fd_offset;
-
down_write(¤t->mm->mmap_sem);
do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
up_write(¤t->mm->mmap_sem);
@@ -393,10 +376,9 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
down_write(¤t->mm->mmap_sem);
error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
- PROT_READ | PROT_EXEC,
- MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
- MAP_EXECUTABLE | MAP_32BIT,
- fd_offset);
+ PROT_READ | PROT_EXEC,
+ MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE | MAP_32BIT,
+ fd_offset);
up_write(¤t->mm->mmap_sem);
if (error != N_TXTADDR(ex)) {
@@ -405,10 +387,9 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
}
down_write(¤t->mm->mmap_sem);
- error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
+ error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
PROT_READ | PROT_WRITE | PROT_EXEC,
- MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
- MAP_EXECUTABLE | MAP_32BIT,
+ MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE | MAP_32BIT,
fd_offset + ex.a_text);
up_write(¤t->mm->mmap_sem);
if (error != N_DATADDR(ex)) {
@@ -422,9 +403,9 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
set_brk(current->mm->start_brk, current->mm->brk);
retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
- if (retval < 0) {
- /* Someone check-me: is this error path enough? */
- send_sig(SIGKILL, current, 0);
+ if (retval < 0) {
+ /* Someone check-me: is this error path enough? */
+ send_sig(SIGKILL, current, 0);
return retval;
}
@@ -433,10 +414,10 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
/* start thread */
asm volatile("movl %0,%%fs" :: "r" (0)); \
asm volatile("movl %0,%%es; movl %0,%%ds": :"r" (__USER32_DS));
- load_gs_index(0);
- (regs)->ip = ex.a_entry;
- (regs)->sp = current->mm->start_stack;
- (regs)->flags = 0x200;
+ load_gs_index(0);
+ (regs)->rip = ex.a_entry;
+ (regs)->rsp = current->mm->start_stack;
+ (regs)->eflags = 0x200;
(regs)->cs = __USER32_CS;
(regs)->ss = __USER32_DS;
regs->r8 = regs->r9 = regs->r10 = regs->r11 =
@@ -444,7 +425,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
set_fs(USER_DS);
if (unlikely(current->ptrace & PT_PTRACED)) {
if (current->ptrace & PT_TRACE_EXEC)
- ptrace_notify((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
+ ptrace_notify ((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
else
send_sig(SIGTRAP, current, 0);
}
@@ -453,8 +434,9 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
static int load_aout_library(struct file *file)
{
- struct inode *inode;
- unsigned long bss, start_addr, len, error;
+ struct inode * inode;
+ unsigned long bss, start_addr, len;
+ unsigned long error;
int retval;
struct exec ex;
@@ -468,8 +450,7 @@ static int load_aout_library(struct file *file)
/* We come in here for the regular a.out style of shared libraries */
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) ||
N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) ||
- i_size_read(inode) <
- ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
+ i_size_read(inode) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
goto out;
}
@@ -486,10 +467,10 @@ static int load_aout_library(struct file *file)
#ifdef WARN_OLD
static unsigned long error_time;
- if (time_after(jiffies, error_time + 5*HZ)) {
- printk(KERN_WARNING
- "N_TXTOFF is not page aligned. Please convert "
- "library: %s\n",
+ if ((jiffies-error_time) > 5*HZ)
+ {
+ printk(KERN_WARNING
+ "N_TXTOFF is not page aligned. Please convert library: %s\n",
file->f_path.dentry->d_name.name);
error_time = jiffies;
}
@@ -497,12 +478,11 @@ static int load_aout_library(struct file *file)
down_write(¤t->mm->mmap_sem);
do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
up_write(¤t->mm->mmap_sem);
-
+
file->f_op->read(file, (char __user *)start_addr,
ex.a_text + ex.a_data, &pos);
flush_icache_range((unsigned long) start_addr,
- (unsigned long) start_addr + ex.a_text +
- ex.a_data);
+ (unsigned long) start_addr + ex.a_text + ex.a_data);
retval = 0;
goto out;
diff --git a/trunk/arch/x86/ia32/ia32_binfmt.c b/trunk/arch/x86/ia32/ia32_binfmt.c
new file mode 100644
index 000000000000..55822d2cf053
--- /dev/null
+++ b/trunk/arch/x86/ia32/ia32_binfmt.c
@@ -0,0 +1,285 @@
+/*
+ * Written 2000,2002 by Andi Kleen.
+ *
+ * Loosely based on the sparc64 and IA64 32bit emulation loaders.
+ * This tricks binfmt_elf.c into loading 32bit binaries using lots
+ * of ugly preprocessor tricks. Talk about very very poor man's inheritance.
+ */
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#undef ELF_ARCH
+#undef ELF_CLASS
+#define ELF_CLASS ELFCLASS32
+#define ELF_ARCH EM_386
+
+#undef elfhdr
+#undef elf_phdr
+#undef elf_note
+#undef elf_addr_t
+#define elfhdr elf32_hdr
+#define elf_phdr elf32_phdr
+#define elf_note elf32_note
+#define elf_addr_t Elf32_Off
+
+#define ELF_NAME "elf/i386"
+
+#define AT_SYSINFO 32
+#define AT_SYSINFO_EHDR 33
+
+int sysctl_vsyscall32 = 1;
+
+#undef ARCH_DLINFO
+#define ARCH_DLINFO do { \
+ if (sysctl_vsyscall32) { \
+ current->mm->context.vdso = (void *)VSYSCALL32_BASE; \
+ NEW_AUX_ENT(AT_SYSINFO, (u32)(u64)VSYSCALL32_VSYSCALL); \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, VSYSCALL32_BASE); \
+ } \
+} while(0)
+
+struct file;
+
+#define IA32_EMULATOR 1
+
+#undef ELF_ET_DYN_BASE
+
+#define ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000)
+
+#define jiffies_to_timeval(a,b) do { (b)->tv_usec = 0; (b)->tv_sec = (a)/HZ; }while(0)
+
+#define _GET_SEG(x) \
+ ({ __u32 seg; asm("movl %%" __stringify(x) ",%0" : "=r"(seg)); seg; })
+
+/* Assumes current==process to be dumped */
+#undef ELF_CORE_COPY_REGS
+#define ELF_CORE_COPY_REGS(pr_reg, regs) \
+ pr_reg[0] = regs->rbx; \
+ pr_reg[1] = regs->rcx; \
+ pr_reg[2] = regs->rdx; \
+ pr_reg[3] = regs->rsi; \
+ pr_reg[4] = regs->rdi; \
+ pr_reg[5] = regs->rbp; \
+ pr_reg[6] = regs->rax; \
+ pr_reg[7] = _GET_SEG(ds); \
+ pr_reg[8] = _GET_SEG(es); \
+ pr_reg[9] = _GET_SEG(fs); \
+ pr_reg[10] = _GET_SEG(gs); \
+ pr_reg[11] = regs->orig_rax; \
+ pr_reg[12] = regs->rip; \
+ pr_reg[13] = regs->cs; \
+ pr_reg[14] = regs->eflags; \
+ pr_reg[15] = regs->rsp; \
+ pr_reg[16] = regs->ss;
+
+
+#define elf_prstatus compat_elf_prstatus
+#define elf_prpsinfo compat_elf_prpsinfo
+#define elf_fpregset_t struct user_i387_ia32_struct
+#define elf_fpxregset_t struct user32_fxsr_struct
+#define user user32
+
+#undef elf_read_implies_exec
+#define elf_read_implies_exec(ex, executable_stack) (executable_stack != EXSTACK_DISABLE_X)
+
+#define elf_core_copy_regs elf32_core_copy_regs
+static inline void elf32_core_copy_regs(compat_elf_gregset_t *elfregs,
+ struct pt_regs *regs)
+{
+ ELF_CORE_COPY_REGS((&elfregs->ebx), regs)
+}
+
+#define elf_core_copy_task_regs elf32_core_copy_task_regs
+static inline int elf32_core_copy_task_regs(struct task_struct *t,
+ compat_elf_gregset_t* elfregs)
+{
+ struct pt_regs *pp = task_pt_regs(t);
+ ELF_CORE_COPY_REGS((&elfregs->ebx), pp);
+ /* fix wrong segments */
+ elfregs->ds = t->thread.ds;
+ elfregs->fs = t->thread.fsindex;
+ elfregs->gs = t->thread.gsindex;
+ elfregs->es = t->thread.es;
+ return 1;
+}
+
+#define elf_core_copy_task_fpregs elf32_core_copy_task_fpregs
+static inline int
+elf32_core_copy_task_fpregs(struct task_struct *tsk, struct pt_regs *regs,
+ elf_fpregset_t *fpu)
+{
+ struct _fpstate_ia32 *fpstate = (void*)fpu;
+ mm_segment_t oldfs = get_fs();
+
+ if (!tsk_used_math(tsk))
+ return 0;
+ if (!regs)
+ regs = task_pt_regs(tsk);
+ if (tsk == current)
+ unlazy_fpu(tsk);
+ set_fs(KERNEL_DS);
+ save_i387_ia32(tsk, fpstate, regs, 1);
+ /* Correct for i386 bug. It puts the fop into the upper 16bits of
+ the tag word (like FXSAVE), not into the fcs*/
+ fpstate->cssel |= fpstate->tag & 0xffff0000;
+ set_fs(oldfs);
+ return 1;
+}
+
+#define ELF_CORE_COPY_XFPREGS 1
+#define ELF_CORE_XFPREG_TYPE NT_PRXFPREG
+#define elf_core_copy_task_xfpregs elf32_core_copy_task_xfpregs
+static inline int
+elf32_core_copy_task_xfpregs(struct task_struct *t, elf_fpxregset_t *xfpu)
+{
+ struct pt_regs *regs = task_pt_regs(t);
+ if (!tsk_used_math(t))
+ return 0;
+ if (t == current)
+ unlazy_fpu(t);
+ memcpy(xfpu, &t->thread.i387.fxsave, sizeof(elf_fpxregset_t));
+ xfpu->fcs = regs->cs;
+ xfpu->fos = t->thread.ds; /* right? */
+ return 1;
+}
+
+#undef elf_check_arch
+#define elf_check_arch(x) \
+ ((x)->e_machine == EM_386)
+
+extern int force_personality32;
+
+#undef ELF_EXEC_PAGESIZE
+#undef ELF_HWCAP
+#undef ELF_PLATFORM
+#undef SET_PERSONALITY
+#define ELF_EXEC_PAGESIZE PAGE_SIZE
+#define ELF_HWCAP (boot_cpu_data.x86_capability[0])
+#define ELF_PLATFORM ("i686")
+#define SET_PERSONALITY(ex, ibcs2) \
+do { \
+ unsigned long new_flags = 0; \
+ if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \
+ new_flags = _TIF_IA32; \
+ if ((current_thread_info()->flags & _TIF_IA32) \
+ != new_flags) \
+ set_thread_flag(TIF_ABI_PENDING); \
+ else \
+ clear_thread_flag(TIF_ABI_PENDING); \
+ /* XXX This overwrites the user set personality */ \
+ current->personality |= force_personality32; \
+} while (0)
+
+/* Override some function names */
+#define elf_format elf32_format
+
+#define init_elf_binfmt init_elf32_binfmt
+#define exit_elf_binfmt exit_elf32_binfmt
+
+#define load_elf_binary load_elf32_binary
+
+#undef ELF_PLAT_INIT
+#define ELF_PLAT_INIT(r, load_addr) elf32_init(r)
+
+#undef start_thread
+#define start_thread(regs,new_rip,new_rsp) do { \
+ asm volatile("movl %0,%%fs" :: "r" (0)); \
+ asm volatile("movl %0,%%es; movl %0,%%ds": :"r" (__USER32_DS)); \
+ load_gs_index(0); \
+ (regs)->rip = (new_rip); \
+ (regs)->rsp = (new_rsp); \
+ (regs)->eflags = 0x200; \
+ (regs)->cs = __USER32_CS; \
+ (regs)->ss = __USER32_DS; \
+ set_fs(USER_DS); \
+} while(0)
+
+
+#include
+
+MODULE_DESCRIPTION("Binary format loader for compatibility with IA32 ELF binaries.");
+MODULE_AUTHOR("Eric Youngdale, Andi Kleen");
+
+#undef MODULE_DESCRIPTION
+#undef MODULE_AUTHOR
+
+static void elf32_init(struct pt_regs *);
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+#define arch_setup_additional_pages syscall32_setup_pages
+extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
+
+#include "../../../fs/binfmt_elf.c"
+
+static void elf32_init(struct pt_regs *regs)
+{
+ struct task_struct *me = current;
+ regs->rdi = 0;
+ regs->rsi = 0;
+ regs->rdx = 0;
+ regs->rcx = 0;
+ regs->rax = 0;
+ regs->rbx = 0;
+ regs->rbp = 0;
+ regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
+ regs->r13 = regs->r14 = regs->r15 = 0;
+ me->thread.fs = 0;
+ me->thread.gs = 0;
+ me->thread.fsindex = 0;
+ me->thread.gsindex = 0;
+ me->thread.ds = __USER_DS;
+ me->thread.es = __USER_DS;
+}
+
+#ifdef CONFIG_SYSCTL
+/* Register vsyscall32 into the ABI table */
+#include
+
+static ctl_table abi_table2[] = {
+ {
+ .procname = "vsyscall32",
+ .data = &sysctl_vsyscall32,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {}
+};
+
+static ctl_table abi_root_table2[] = {
+ {
+ .ctl_name = CTL_ABI,
+ .procname = "abi",
+ .mode = 0555,
+ .child = abi_table2
+ },
+ {}
+};
+
+static __init int ia32_binfmt_init(void)
+{
+ register_sysctl_table(abi_root_table2);
+ return 0;
+}
+__initcall(ia32_binfmt_init);
+#endif
diff --git a/trunk/arch/x86/ia32/ia32_signal.c b/trunk/arch/x86/ia32/ia32_signal.c
index 1c0503bdfb1a..6ea19c25f90d 100644
--- a/trunk/arch/x86/ia32/ia32_signal.c
+++ b/trunk/arch/x86/ia32/ia32_signal.c
@@ -29,8 +29,9 @@
#include
#include
#include
+#include
#include
-#include
+#include
#define DEBUG_SIG 0
@@ -42,8 +43,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
{
int err;
-
- if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
+ if (!access_ok (VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
return -EFAULT;
/* If you change siginfo_t structure, please make sure that
@@ -53,19 +53,16 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
3 ints plus the relevant union member. */
err = __put_user(from->si_signo, &to->si_signo);
err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user((short)from->si_code, &to->si_code);
+ err |= __put_user((short)from->si_code, &to->si_code);
if (from->si_code < 0) {
err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(ptr_to_compat(from->si_ptr), &to->si_ptr);
+ err |= __put_user(from->si_uid, &to->si_uid);
+ err |= __put_user(ptr_to_compat(from->si_ptr), &to->si_ptr);
} else {
- /*
- * First 32bits of unions are always present:
- * si_pid === si_band === si_tid === si_addr(LS half)
- */
- err |= __put_user(from->_sifields._pad[0],
- &to->_sifields._pad[0]);
+ /* First 32bits of unions are always present:
+ * si_pid === si_band === si_tid === si_addr(LS half) */
+ err |= __put_user(from->_sifields._pad[0], &to->_sifields._pad[0]);
switch (from->si_code >> 16) {
case __SI_FAULT >> 16:
break;
@@ -79,15 +76,14 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
err |= __put_user(from->si_uid, &to->si_uid);
break;
case __SI_POLL >> 16:
- err |= __put_user(from->si_fd, &to->si_fd);
+ err |= __put_user(from->si_fd, &to->si_fd);
break;
case __SI_TIMER >> 16:
- err |= __put_user(from->si_overrun, &to->si_overrun);
+ err |= __put_user(from->si_overrun, &to->si_overrun);
err |= __put_user(ptr_to_compat(from->si_ptr),
- &to->si_ptr);
+ &to->si_ptr);
break;
- /* This is not generated by the kernel as of now. */
- case __SI_RT >> 16:
+ case __SI_RT >> 16: /* This is not generated by the kernel as of now. */
case __SI_MESGQ >> 16:
err |= __put_user(from->si_uid, &to->si_uid);
err |= __put_user(from->si_int, &to->si_int);
@@ -101,8 +97,7 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
{
int err;
u32 ptr32;
-
- if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
+ if (!access_ok (VERIFY_READ, from, sizeof(compat_siginfo_t)))
return -EFAULT;
err = __get_user(to->si_signo, &from->si_signo);
@@ -117,7 +112,8 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
return err;
}
-asmlinkage long sys32_sigsuspend(int history0, int history1, old_sigset_t mask)
+asmlinkage long
+sys32_sigsuspend(int history0, int history1, old_sigset_t mask)
{
mask &= _BLOCKABLE;
spin_lock_irq(¤t->sighand->siglock);
@@ -132,37 +128,36 @@ asmlinkage long sys32_sigsuspend(int history0, int history1, old_sigset_t mask)
return -ERESTARTNOHAND;
}
-asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
- stack_ia32_t __user *uoss_ptr,
- struct pt_regs *regs)
+asmlinkage long
+sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
+ stack_ia32_t __user *uoss_ptr,
+ struct pt_regs *regs)
{
- stack_t uss, uoss;
+ stack_t uss,uoss;
int ret;
- mm_segment_t seg;
-
- if (uss_ptr) {
+ mm_segment_t seg;
+ if (uss_ptr) {
u32 ptr;
-
- memset(&uss, 0, sizeof(stack_t));
- if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)) ||
+ memset(&uss,0,sizeof(stack_t));
+ if (!access_ok(VERIFY_READ,uss_ptr,sizeof(stack_ia32_t)) ||
__get_user(ptr, &uss_ptr->ss_sp) ||
__get_user(uss.ss_flags, &uss_ptr->ss_flags) ||
__get_user(uss.ss_size, &uss_ptr->ss_size))
return -EFAULT;
uss.ss_sp = compat_ptr(ptr);
}
- seg = get_fs();
- set_fs(KERNEL_DS);
- ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp);
- set_fs(seg);
+ seg = get_fs();
+ set_fs(KERNEL_DS);
+ ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->rsp);
+ set_fs(seg);
if (ret >= 0 && uoss_ptr) {
- if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)) ||
+ if (!access_ok(VERIFY_WRITE,uoss_ptr,sizeof(stack_ia32_t)) ||
__put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) ||
__put_user(uoss.ss_flags, &uoss_ptr->ss_flags) ||
__put_user(uoss.ss_size, &uoss_ptr->ss_size))
ret = -EFAULT;
- }
- return ret;
+ }
+ return ret;
}
/*
@@ -191,85 +186,87 @@ struct rt_sigframe
char retcode[8];
};
-#define COPY(x) { \
- unsigned int reg; \
- err |= __get_user(reg, &sc->x); \
- regs->x = reg; \
-}
-
-#define RELOAD_SEG(seg,mask) \
- { unsigned int cur; \
- unsigned short pre; \
- err |= __get_user(pre, &sc->seg); \
- asm volatile("movl %%" #seg ",%0" : "=r" (cur)); \
- pre |= mask; \
- if (pre != cur) loadsegment(seg, pre); }
-
-static int ia32_restore_sigcontext(struct pt_regs *regs,
- struct sigcontext_ia32 __user *sc,
- unsigned int *peax)
+static int
+ia32_restore_sigcontext(struct pt_regs *regs, struct sigcontext_ia32 __user *sc, unsigned int *peax)
{
- unsigned int tmpflags, gs, oldgs, err = 0;
- struct _fpstate_ia32 __user *buf;
- u32 tmp;
-
+ unsigned int err = 0;
+
/* Always make any pending restarted system calls return -EINTR */
current_thread_info()->restart_block.fn = do_no_restart_syscall;
#if DEBUG_SIG
- printk(KERN_DEBUG "SIG restore_sigcontext: "
- "sc=%p err(%x) eip(%x) cs(%x) flg(%x)\n",
- sc, sc->err, sc->ip, sc->cs, sc->flags);
+ printk("SIG restore_sigcontext: sc=%p err(%x) eip(%x) cs(%x) flg(%x)\n",
+ sc, sc->err, sc->eip, sc->cs, sc->eflags);
#endif
+#define COPY(x) { \
+ unsigned int reg; \
+ err |= __get_user(reg, &sc->e ##x); \
+ regs->r ## x = reg; \
+}
- /*
- * Reload fs and gs if they have changed in the signal
- * handler. This does not handle long fs/gs base changes in
- * the handler, but does not clobber them at least in the
- * normal case.
- */
- err |= __get_user(gs, &sc->gs);
- gs |= 3;
- asm("movl %%gs,%0" : "=r" (oldgs));
- if (gs != oldgs)
- load_gs_index(gs);
-
- RELOAD_SEG(fs, 3);
- RELOAD_SEG(ds, 3);
- RELOAD_SEG(es, 3);
+#define RELOAD_SEG(seg,mask) \
+ { unsigned int cur; \
+ unsigned short pre; \
+ err |= __get_user(pre, &sc->seg); \
+ asm volatile("movl %%" #seg ",%0" : "=r" (cur)); \
+ pre |= mask; \
+ if (pre != cur) loadsegment(seg,pre); }
+
+ /* Reload fs and gs if they have changed in the signal handler.
+ This does not handle long fs/gs base changes in the handler, but
+ does not clobber them at least in the normal case. */
+
+ {
+ unsigned gs, oldgs;
+ err |= __get_user(gs, &sc->gs);
+ gs |= 3;
+ asm("movl %%gs,%0" : "=r" (oldgs));
+ if (gs != oldgs)
+ load_gs_index(gs);
+ }
+ RELOAD_SEG(fs,3);
+ RELOAD_SEG(ds,3);
+ RELOAD_SEG(es,3);
COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
COPY(dx); COPY(cx); COPY(ip);
- /* Don't touch extended registers */
-
- err |= __get_user(regs->cs, &sc->cs);
- regs->cs |= 3;
- err |= __get_user(regs->ss, &sc->ss);
- regs->ss |= 3;
-
- err |= __get_user(tmpflags, &sc->flags);
- regs->flags = (regs->flags & ~0x40DD5) | (tmpflags & 0x40DD5);
- /* disable syscall checks */
- regs->orig_ax = -1;
-
- err |= __get_user(tmp, &sc->fpstate);
- buf = compat_ptr(tmp);
- if (buf) {
- if (!access_ok(VERIFY_READ, buf, sizeof(*buf)))
- goto badframe;
- err |= restore_i387_ia32(buf);
- } else {
- struct task_struct *me = current;
+ /* Don't touch extended registers */
+
+ err |= __get_user(regs->cs, &sc->cs);
+ regs->cs |= 3;
+ err |= __get_user(regs->ss, &sc->ss);
+ regs->ss |= 3;
+
+ {
+ unsigned int tmpflags;
+ err |= __get_user(tmpflags, &sc->eflags);
+ regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5);
+ regs->orig_rax = -1; /* disable syscall checks */
+ }
- if (used_math()) {
- clear_fpu(me);
- clear_used_math();
+ {
+ u32 tmp;
+ struct _fpstate_ia32 __user * buf;
+ err |= __get_user(tmp, &sc->fpstate);
+ buf = compat_ptr(tmp);
+ if (buf) {
+ if (!access_ok(VERIFY_READ, buf, sizeof(*buf)))
+ goto badframe;
+ err |= restore_i387_ia32(current, buf, 0);
+ } else {
+ struct task_struct *me = current;
+ if (used_math()) {
+ clear_fpu(me);
+ clear_used_math();
+ }
}
}
- err |= __get_user(tmp, &sc->ax);
- *peax = tmp;
-
+ {
+ u32 tmp;
+ err |= __get_user(tmp, &sc->eax);
+ *peax = tmp;
+ }
return err;
badframe:
@@ -278,16 +275,15 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
asmlinkage long sys32_sigreturn(struct pt_regs *regs)
{
- struct sigframe __user *frame = (struct sigframe __user *)(regs->sp-8);
+ struct sigframe __user *frame = (struct sigframe __user *)(regs->rsp-8);
sigset_t set;
- unsigned int ax;
+ unsigned int eax;
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
if (__get_user(set.sig[0], &frame->sc.oldmask)
|| (_COMPAT_NSIG_WORDS > 1
- && __copy_from_user((((char *) &set.sig) + 4),
- &frame->extramask,
+ && __copy_from_user((((char *) &set.sig) + 4), &frame->extramask,
sizeof(frame->extramask))))
goto badframe;
@@ -296,24 +292,24 @@ asmlinkage long sys32_sigreturn(struct pt_regs *regs)
current->blocked = set;
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
-
- if (ia32_restore_sigcontext(regs, &frame->sc, &ax))
+
+ if (ia32_restore_sigcontext(regs, &frame->sc, &eax))
goto badframe;
- return ax;
+ return eax;
badframe:
signal_fault(regs, frame, "32bit sigreturn");
return 0;
-}
+}
asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
sigset_t set;
- unsigned int ax;
+ unsigned int eax;
struct pt_regs tregs;
- frame = (struct rt_sigframe __user *)(regs->sp - 4);
+ frame = (struct rt_sigframe __user *)(regs->rsp - 4);
if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
goto badframe;
@@ -325,28 +321,28 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs)
current->blocked = set;
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
-
- if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+
+ if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax))
goto badframe;
tregs = *regs;
if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
goto badframe;
- return ax;
+ return eax;
badframe:
- signal_fault(regs, frame, "32bit rt sigreturn");
+ signal_fault(regs,frame,"32bit rt sigreturn");
return 0;
-}
+}
/*
* Set up a signal frame.
*/
-static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
- struct _fpstate_ia32 __user *fpstate,
- struct pt_regs *regs, unsigned int mask)
+static int
+ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, struct _fpstate_ia32 __user *fpstate,
+ struct pt_regs *regs, unsigned int mask)
{
int tmp, err = 0;
@@ -360,26 +356,26 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
__asm__("movl %%es,%0" : "=r"(tmp): "0"(tmp));
err |= __put_user(tmp, (unsigned int __user *)&sc->es);
- err |= __put_user((u32)regs->di, &sc->di);
- err |= __put_user((u32)regs->si, &sc->si);
- err |= __put_user((u32)regs->bp, &sc->bp);
- err |= __put_user((u32)regs->sp, &sc->sp);
- err |= __put_user((u32)regs->bx, &sc->bx);
- err |= __put_user((u32)regs->dx, &sc->dx);
- err |= __put_user((u32)regs->cx, &sc->cx);
- err |= __put_user((u32)regs->ax, &sc->ax);
+ err |= __put_user((u32)regs->rdi, &sc->edi);
+ err |= __put_user((u32)regs->rsi, &sc->esi);
+ err |= __put_user((u32)regs->rbp, &sc->ebp);
+ err |= __put_user((u32)regs->rsp, &sc->esp);
+ err |= __put_user((u32)regs->rbx, &sc->ebx);
+ err |= __put_user((u32)regs->rdx, &sc->edx);
+ err |= __put_user((u32)regs->rcx, &sc->ecx);
+ err |= __put_user((u32)regs->rax, &sc->eax);
err |= __put_user((u32)regs->cs, &sc->cs);
err |= __put_user((u32)regs->ss, &sc->ss);
err |= __put_user(current->thread.trap_no, &sc->trapno);
err |= __put_user(current->thread.error_code, &sc->err);
- err |= __put_user((u32)regs->ip, &sc->ip);
- err |= __put_user((u32)regs->flags, &sc->flags);
- err |= __put_user((u32)regs->sp, &sc->sp_at_signal);
+ err |= __put_user((u32)regs->rip, &sc->eip);
+ err |= __put_user((u32)regs->eflags, &sc->eflags);
+ err |= __put_user((u32)regs->rsp, &sc->esp_at_signal);
- tmp = save_i387_ia32(fpstate);
+ tmp = save_i387_ia32(current, fpstate, regs, 0);
if (tmp < 0)
err = -EFAULT;
- else {
+ else {
clear_used_math();
stts();
err |= __put_user(ptr_to_compat(tmp ? fpstate : NULL),
@@ -396,53 +392,40 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
/*
* Determine which stack to use..
*/
-static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
- size_t frame_size)
+static void __user *
+get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
{
- unsigned long sp;
+ unsigned long rsp;
/* Default to using normal stack */
- sp = regs->sp;
+ rsp = regs->rsp;
/* This is the X/Open sanctioned signal stack switching. */
if (ka->sa.sa_flags & SA_ONSTACK) {
- if (sas_ss_flags(sp) == 0)
- sp = current->sas_ss_sp + current->sas_ss_size;
+ if (sas_ss_flags(rsp) == 0)
+ rsp = current->sas_ss_sp + current->sas_ss_size;
}
/* This is the legacy signal stack switching. */
else if ((regs->ss & 0xffff) != __USER_DS &&
!(ka->sa.sa_flags & SA_RESTORER) &&
- ka->sa.sa_restorer)
- sp = (unsigned long) ka->sa.sa_restorer;
+ ka->sa.sa_restorer) {
+ rsp = (unsigned long) ka->sa.sa_restorer;
+ }
- sp -= frame_size;
+ rsp -= frame_size;
/* Align the stack pointer according to the i386 ABI,
* i.e. so that on function entry ((sp + 4) & 15) == 0. */
- sp = ((sp + 4) & -16ul) - 4;
- return (void __user *) sp;
+ rsp = ((rsp + 4) & -16ul) - 4;
+ return (void __user *) rsp;
}
int ia32_setup_frame(int sig, struct k_sigaction *ka,
- compat_sigset_t *set, struct pt_regs *regs)
+ compat_sigset_t *set, struct pt_regs * regs)
{
struct sigframe __user *frame;
- void __user *restorer;
int err = 0;
- /* copy_to_user optimizes that into a single 8 byte store */
- static const struct {
- u16 poplmovl;
- u32 val;
- u16 int80;
- u16 pad;
- } __attribute__((packed)) code = {
- 0xb858, /* popl %eax ; movl $...,%eax */
- __NR_ia32_sigreturn,
- 0x80cd, /* int $0x80 */
- 0,
- };
-
frame = get_sigframe(ka, regs, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
@@ -460,53 +443,64 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
if (_COMPAT_NSIG_WORDS > 1) {
err |= __copy_to_user(frame->extramask, &set->sig[1],
sizeof(frame->extramask));
- if (err)
- goto give_sigsegv;
}
+ if (err)
+ goto give_sigsegv;
- if (ka->sa.sa_flags & SA_RESTORER) {
- restorer = ka->sa.sa_restorer;
- } else {
- /* Return stub is in 32bit vsyscall page */
+ /* Return stub is in 32bit vsyscall page */
+ {
+ void __user *restorer;
if (current->binfmt->hasvdso)
- restorer = VDSO32_SYMBOL(current->mm->context.vdso,
- sigreturn);
+ restorer = VSYSCALL32_SIGRETURN;
else
- restorer = &frame->retcode;
+ restorer = (void *)&frame->retcode;
+ if (ka->sa.sa_flags & SA_RESTORER)
+ restorer = ka->sa.sa_restorer;
+ err |= __put_user(ptr_to_compat(restorer), &frame->pretcode);
+ }
+ /* These are actually not used anymore, but left because some
+ gdb versions depend on them as a marker. */
+ {
+ /* copy_to_user optimizes that into a single 8 byte store */
+ static const struct {
+ u16 poplmovl;
+ u32 val;
+ u16 int80;
+ u16 pad;
+ } __attribute__((packed)) code = {
+ 0xb858, /* popl %eax ; movl $...,%eax */
+ __NR_ia32_sigreturn,
+ 0x80cd, /* int $0x80 */
+ 0,
+ };
+ err |= __copy_to_user(frame->retcode, &code, 8);
}
- err |= __put_user(ptr_to_compat(restorer), &frame->pretcode);
-
- /*
- * These are actually not used anymore, but left because some
- * gdb versions depend on them as a marker.
- */
- err |= __copy_to_user(frame->retcode, &code, 8);
if (err)
goto give_sigsegv;
/* Set up registers for signal handler */
- regs->sp = (unsigned long) frame;
- regs->ip = (unsigned long) ka->sa.sa_handler;
+ regs->rsp = (unsigned long) frame;
+ regs->rip = (unsigned long) ka->sa.sa_handler;
/* Make -mregparm=3 work */
- regs->ax = sig;
- regs->dx = 0;
- regs->cx = 0;
+ regs->rax = sig;
+ regs->rdx = 0;
+ regs->rcx = 0;
- asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
- asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+ asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
+ asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
- regs->cs = __USER32_CS;
- regs->ss = __USER32_DS;
+ regs->cs = __USER32_CS;
+ regs->ss = __USER32_DS;
set_fs(USER_DS);
- regs->flags &= ~X86_EFLAGS_TF;
+ regs->eflags &= ~TF_MASK;
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#if DEBUG_SIG
- printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
- current->comm, current->pid, frame, regs->ip, frame->pretcode);
+ printk("SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
+ current->comm, current->pid, frame, regs->rip, frame->pretcode);
#endif
return 0;
@@ -517,34 +511,25 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
}
int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
- compat_sigset_t *set, struct pt_regs *regs)
+ compat_sigset_t *set, struct pt_regs * regs)
{
struct rt_sigframe __user *frame;
- struct exec_domain *ed = current_thread_info()->exec_domain;
- void __user *restorer;
int err = 0;
- /* __copy_to_user optimizes that into a single 8 byte store */
- static const struct {
- u8 movl;
- u32 val;
- u16 int80;
- u16 pad;
- u8 pad2;
- } __attribute__((packed)) code = {
- 0xb8,
- __NR_ia32_rt_sigreturn,
- 0x80cd,
- 0,
- };
-
frame = get_sigframe(ka, regs, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
- err |= __put_user((ed && ed->signal_invmap && sig < 32
- ? ed->signal_invmap[sig] : sig), &frame->sig);
+ {
+ struct exec_domain *ed = current_thread_info()->exec_domain;
+ err |= __put_user((ed
+ && ed->signal_invmap
+ && sig < 32
+ ? ed->signal_invmap[sig]
+ : sig),
+ &frame->sig);
+ }
err |= __put_user(ptr_to_compat(&frame->info), &frame->pinfo);
err |= __put_user(ptr_to_compat(&frame->uc), &frame->puc);
err |= copy_siginfo_to_user32(&frame->info, info);
@@ -555,58 +540,73 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(regs->sp),
+ err |= __put_user(sas_ss_flags(regs->rsp),
&frame->uc.uc_stack.ss_flags);
err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
- regs, set->sig[0]);
+ regs, set->sig[0]);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
goto give_sigsegv;
- if (ka->sa.sa_flags & SA_RESTORER)
- restorer = ka->sa.sa_restorer;
- else
- restorer = VDSO32_SYMBOL(current->mm->context.vdso,
- rt_sigreturn);
- err |= __put_user(ptr_to_compat(restorer), &frame->pretcode);
-
- /*
- * Not actually used anymore, but left because some gdb
- * versions need it.
- */
- err |= __copy_to_user(frame->retcode, &code, 8);
+
+ {
+ void __user *restorer = VSYSCALL32_RTSIGRETURN;
+ if (ka->sa.sa_flags & SA_RESTORER)
+ restorer = ka->sa.sa_restorer;
+ err |= __put_user(ptr_to_compat(restorer), &frame->pretcode);
+ }
+
+ /* This is movl $,%eax ; int $0x80 */
+ /* Not actually used anymore, but left because some gdb versions
+ need it. */
+ {
+ /* __copy_to_user optimizes that into a single 8 byte store */
+ static const struct {
+ u8 movl;
+ u32 val;
+ u16 int80;
+ u16 pad;
+ u8 pad2;
+ } __attribute__((packed)) code = {
+ 0xb8,
+ __NR_ia32_rt_sigreturn,
+ 0x80cd,
+ 0,
+ };
+ err |= __copy_to_user(frame->retcode, &code, 8);
+ }
if (err)
goto give_sigsegv;
/* Set up registers for signal handler */
- regs->sp = (unsigned long) frame;
- regs->ip = (unsigned long) ka->sa.sa_handler;
+ regs->rsp = (unsigned long) frame;
+ regs->rip = (unsigned long) ka->sa.sa_handler;
/* Make -mregparm=3 work */
- regs->ax = sig;
- regs->dx = (unsigned long) &frame->info;
- regs->cx = (unsigned long) &frame->uc;
+ regs->rax = sig;
+ regs->rdx = (unsigned long) &frame->info;
+ regs->rcx = (unsigned long) &frame->uc;
/* Make -mregparm=3 work */
- regs->ax = sig;
- regs->dx = (unsigned long) &frame->info;
- regs->cx = (unsigned long) &frame->uc;
-
- asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
- asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+ regs->rax = sig;
+ regs->rdx = (unsigned long) &frame->info;
+ regs->rcx = (unsigned long) &frame->uc;
- regs->cs = __USER32_CS;
- regs->ss = __USER32_DS;
+ asm volatile("movl %0,%%ds" :: "r" (__USER32_DS));
+ asm volatile("movl %0,%%es" :: "r" (__USER32_DS));
+
+ regs->cs = __USER32_CS;
+ regs->ss = __USER32_DS;
set_fs(USER_DS);
- regs->flags &= ~X86_EFLAGS_TF;
+ regs->eflags &= ~TF_MASK;
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#if DEBUG_SIG
- printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
- current->comm, current->pid, frame, regs->ip, frame->pretcode);
+ printk("SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
+ current->comm, current->pid, frame, regs->rip, frame->pretcode);
#endif
return 0;
diff --git a/trunk/arch/x86/ia32/ia32entry.S b/trunk/arch/x86/ia32/ia32entry.S
index 0db0a6291bbd..df588f0f76e1 100644
--- a/trunk/arch/x86/ia32/ia32entry.S
+++ b/trunk/arch/x86/ia32/ia32entry.S
@@ -12,6 +12,7 @@
#include
#include
#include
+#include
#include
#include
@@ -103,7 +104,7 @@ ENTRY(ia32_sysenter_target)
pushfq
CFI_ADJUST_CFA_OFFSET 8
/*CFI_REL_OFFSET rflags,0*/
- movl 8*3-THREAD_SIZE+threadinfo_sysenter_return(%rsp), %r10d
+ movl $VSYSCALL32_SYSEXIT, %r10d
CFI_REGISTER rip,r10
pushq $__USER32_CS
CFI_ADJUST_CFA_OFFSET 8
@@ -141,8 +142,6 @@ sysenter_do_call:
andl $~TS_COMPAT,threadinfo_status(%r10)
/* clear IF, that popfq doesn't enable interrupts early */
andl $~0x200,EFLAGS-R11(%rsp)
- movl RIP-R11(%rsp),%edx /* User %eip */
- CFI_REGISTER rip,rdx
RESTORE_ARGS 1,24,1,1,1,1
popfq
CFI_ADJUST_CFA_OFFSET -8
@@ -150,6 +149,8 @@ sysenter_do_call:
popq %rcx /* User %esp */
CFI_ADJUST_CFA_OFFSET -8
CFI_REGISTER rsp,rcx
+ movl $VSYSCALL32_SYSEXIT,%edx /* User %eip */
+ CFI_REGISTER rip,rdx
TRACE_IRQS_ON
swapgs
sti /* sti only takes effect after the next instruction */
@@ -643,8 +644,8 @@ ia32_sys_call_table:
.quad compat_sys_futex /* 240 */
.quad compat_sys_sched_setaffinity
.quad compat_sys_sched_getaffinity
- .quad sys_set_thread_area
- .quad sys_get_thread_area
+ .quad sys32_set_thread_area
+ .quad sys32_get_thread_area
.quad compat_sys_io_setup /* 245 */
.quad sys_io_destroy
.quad compat_sys_io_getevents
diff --git a/trunk/arch/x86/ia32/ipc32.c b/trunk/arch/x86/ia32/ipc32.c
index d21991ce606c..7b3342e5aab5 100644
--- a/trunk/arch/x86/ia32/ipc32.c
+++ b/trunk/arch/x86/ia32/ipc32.c
@@ -9,8 +9,9 @@
#include
#include
-asmlinkage long sys32_ipc(u32 call, int first, int second, int third,
- compat_uptr_t ptr, u32 fifth)
+asmlinkage long
+sys32_ipc(u32 call, int first, int second, int third,
+ compat_uptr_t ptr, u32 fifth)
{
int version;
@@ -18,35 +19,36 @@ asmlinkage long sys32_ipc(u32 call, int first, int second, int third,
call &= 0xffff;
switch (call) {
- case SEMOP:
+ case SEMOP:
/* struct sembuf is the same on 32 and 64bit :)) */
return sys_semtimedop(first, compat_ptr(ptr), second, NULL);
- case SEMTIMEDOP:
+ case SEMTIMEDOP:
return compat_sys_semtimedop(first, compat_ptr(ptr), second,
compat_ptr(fifth));
- case SEMGET:
+ case SEMGET:
return sys_semget(first, second, third);
- case SEMCTL:
+ case SEMCTL:
return compat_sys_semctl(first, second, third, compat_ptr(ptr));
- case MSGSND:
+ case MSGSND:
return compat_sys_msgsnd(first, second, third, compat_ptr(ptr));
- case MSGRCV:
+ case MSGRCV:
return compat_sys_msgrcv(first, second, fifth, third,
version, compat_ptr(ptr));
- case MSGGET:
+ case MSGGET:
return sys_msgget((key_t) first, second);
- case MSGCTL:
+ case MSGCTL:
return compat_sys_msgctl(first, second, compat_ptr(ptr));
- case SHMAT:
+ case SHMAT:
return compat_sys_shmat(first, second, third, version,
compat_ptr(ptr));
- case SHMDT:
+ break;
+ case SHMDT:
return sys_shmdt(compat_ptr(ptr));
- case SHMGET:
+ case SHMGET:
return sys_shmget(first, (unsigned)second, third);
- case SHMCTL:
+ case SHMCTL:
return compat_sys_shmctl(first, second, compat_ptr(ptr));
}
return -ENOSYS;
diff --git a/trunk/arch/x86/ia32/mmap32.c b/trunk/arch/x86/ia32/mmap32.c
new file mode 100644
index 000000000000..e4b84b4a417a
--- /dev/null
+++ b/trunk/arch/x86/ia32/mmap32.c
@@ -0,0 +1,79 @@
+/*
+ * linux/arch/x86_64/ia32/mm/mmap.c
+ *
+ * flexible mmap layout support
+ *
+ * Based on the i386 version which was
+ *
+ * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ *
+ * Started by Ingo Molnar
+ */
+
+#include
+#include
+#include
+#include
+
+/*
+ * Top of mmap area (just below the process stack).
+ *
+ * Leave an at least ~128 MB hole.
+ */
+#define MIN_GAP (128*1024*1024)
+#define MAX_GAP (TASK_SIZE/6*5)
+
+static inline unsigned long mmap_base(struct mm_struct *mm)
+{
+ unsigned long gap = current->signal->rlim[RLIMIT_STACK].rlim_cur;
+ unsigned long random_factor = 0;
+
+ if (current->flags & PF_RANDOMIZE)
+ random_factor = get_random_int() % (1024*1024);
+
+ if (gap < MIN_GAP)
+ gap = MIN_GAP;
+ else if (gap > MAX_GAP)
+ gap = MAX_GAP;
+
+ return PAGE_ALIGN(TASK_SIZE - gap - random_factor);
+}
+
+/*
+ * This function, called very early during the creation of a new
+ * process VM image, sets up which VM layout function to use:
+ */
+void ia32_pick_mmap_layout(struct mm_struct *mm)
+{
+ /*
+ * Fall back to the standard layout if the personality
+ * bit is set, or if the expected stack growth is unlimited:
+ */
+ if (sysctl_legacy_va_layout ||
+ (current->personality & ADDR_COMPAT_LAYOUT) ||
+ current->signal->rlim[RLIMIT_STACK].rlim_cur == RLIM_INFINITY) {
+ mm->mmap_base = TASK_UNMAPPED_BASE;
+ mm->get_unmapped_area = arch_get_unmapped_area;
+ mm->unmap_area = arch_unmap_area;
+ } else {
+ mm->mmap_base = mmap_base(mm);
+ mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+ mm->unmap_area = arch_unmap_area_topdown;
+ }
+}
diff --git a/trunk/arch/x86/ia32/ptrace32.c b/trunk/arch/x86/ia32/ptrace32.c
new file mode 100644
index 000000000000..4a233ad6269c
--- /dev/null
+++ b/trunk/arch/x86/ia32/ptrace32.c
@@ -0,0 +1,404 @@
+/*
+ * 32bit ptrace for x86-64.
+ *
+ * Copyright 2001,2002 Andi Kleen, SuSE Labs.
+ * Some parts copied from arch/i386/kernel/ptrace.c. See that file for earlier
+ * copyright.
+ *
+ * This allows to access 64bit processes too; but there is no way to see the extended
+ * register contents.
+ */
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+/*
+ * Determines which flags the user has access to [1 = access, 0 = no access].
+ * Prohibits changing ID(21), VIP(20), VIF(19), VM(17), IOPL(12-13), IF(9).
+ * Also masks reserved bits (31-22, 15, 5, 3, 1).
+ */
+#define FLAG_MASK 0x54dd5UL
+
+#define R32(l,q) \
+ case offsetof(struct user32, regs.l): stack[offsetof(struct pt_regs, q)/8] = val; break
+
+static int putreg32(struct task_struct *child, unsigned regno, u32 val)
+{
+ int i;
+ __u64 *stack = (__u64 *)task_pt_regs(child);
+
+ switch (regno) {
+ case offsetof(struct user32, regs.fs):
+ if (val && (val & 3) != 3) return -EIO;
+ child->thread.fsindex = val & 0xffff;
+ break;
+ case offsetof(struct user32, regs.gs):
+ if (val && (val & 3) != 3) return -EIO;
+ child->thread.gsindex = val & 0xffff;
+ break;
+ case offsetof(struct user32, regs.ds):
+ if (val && (val & 3) != 3) return -EIO;
+ child->thread.ds = val & 0xffff;
+ break;
+ case offsetof(struct user32, regs.es):
+ child->thread.es = val & 0xffff;
+ break;
+ case offsetof(struct user32, regs.ss):
+ if ((val & 3) != 3) return -EIO;
+ stack[offsetof(struct pt_regs, ss)/8] = val & 0xffff;
+ break;
+ case offsetof(struct user32, regs.cs):
+ if ((val & 3) != 3) return -EIO;
+ stack[offsetof(struct pt_regs, cs)/8] = val & 0xffff;
+ break;
+
+ R32(ebx, rbx);
+ R32(ecx, rcx);
+ R32(edx, rdx);
+ R32(edi, rdi);
+ R32(esi, rsi);
+ R32(ebp, rbp);
+ R32(eax, rax);
+ R32(orig_eax, orig_rax);
+ R32(eip, rip);
+ R32(esp, rsp);
+
+ case offsetof(struct user32, regs.eflags): {
+ __u64 *flags = &stack[offsetof(struct pt_regs, eflags)/8];
+ val &= FLAG_MASK;
+ *flags = val | (*flags & ~FLAG_MASK);
+ break;
+ }
+
+ case offsetof(struct user32, u_debugreg[4]):
+ case offsetof(struct user32, u_debugreg[5]):
+ return -EIO;
+
+ case offsetof(struct user32, u_debugreg[0]):
+ child->thread.debugreg0 = val;
+ break;
+
+ case offsetof(struct user32, u_debugreg[1]):
+ child->thread.debugreg1 = val;
+ break;
+
+ case offsetof(struct user32, u_debugreg[2]):
+ child->thread.debugreg2 = val;
+ break;
+
+ case offsetof(struct user32, u_debugreg[3]):
+ child->thread.debugreg3 = val;
+ break;
+
+ case offsetof(struct user32, u_debugreg[6]):
+ child->thread.debugreg6 = val;
+ break;
+
+ case offsetof(struct user32, u_debugreg[7]):
+ val &= ~DR_CONTROL_RESERVED;
+ /* See arch/i386/kernel/ptrace.c for an explanation of
+ * this awkward check.*/
+ for(i=0; i<4; i++)
+ if ((0x5454 >> ((val >> (16 + 4*i)) & 0xf)) & 1)
+ return -EIO;
+ child->thread.debugreg7 = val;
+ if (val)
+ set_tsk_thread_flag(child, TIF_DEBUG);
+ else
+ clear_tsk_thread_flag(child, TIF_DEBUG);
+ break;
+
+ default:
+ if (regno > sizeof(struct user32) || (regno & 3))
+ return -EIO;
+
+ /* Other dummy fields in the virtual user structure are ignored */
+ break;
+ }
+ return 0;
+}
+
+#undef R32
+
+#define R32(l,q) \
+ case offsetof(struct user32, regs.l): *val = stack[offsetof(struct pt_regs, q)/8]; break
+
+static int getreg32(struct task_struct *child, unsigned regno, u32 *val)
+{
+ __u64 *stack = (__u64 *)task_pt_regs(child);
+
+ switch (regno) {
+ case offsetof(struct user32, regs.fs):
+ *val = child->thread.fsindex;
+ break;
+ case offsetof(struct user32, regs.gs):
+ *val = child->thread.gsindex;
+ break;
+ case offsetof(struct user32, regs.ds):
+ *val = child->thread.ds;
+ break;
+ case offsetof(struct user32, regs.es):
+ *val = child->thread.es;
+ break;
+
+ R32(cs, cs);
+ R32(ss, ss);
+ R32(ebx, rbx);
+ R32(ecx, rcx);
+ R32(edx, rdx);
+ R32(edi, rdi);
+ R32(esi, rsi);
+ R32(ebp, rbp);
+ R32(eax, rax);
+ R32(orig_eax, orig_rax);
+ R32(eip, rip);
+ R32(eflags, eflags);
+ R32(esp, rsp);
+
+ case offsetof(struct user32, u_debugreg[0]):
+ *val = child->thread.debugreg0;
+ break;
+ case offsetof(struct user32, u_debugreg[1]):
+ *val = child->thread.debugreg1;
+ break;
+ case offsetof(struct user32, u_debugreg[2]):
+ *val = child->thread.debugreg2;
+ break;
+ case offsetof(struct user32, u_debugreg[3]):
+ *val = child->thread.debugreg3;
+ break;
+ case offsetof(struct user32, u_debugreg[6]):
+ *val = child->thread.debugreg6;
+ break;
+ case offsetof(struct user32, u_debugreg[7]):
+ *val = child->thread.debugreg7;
+ break;
+
+ default:
+ if (regno > sizeof(struct user32) || (regno & 3))
+ return -EIO;
+
+ /* Other dummy fields in the virtual user structure are ignored */
+ *val = 0;
+ break;
+ }
+ return 0;
+}
+
+#undef R32
+
+static long ptrace32_siginfo(unsigned request, u32 pid, u32 addr, u32 data)
+{
+ int ret;
+ compat_siginfo_t __user *si32 = compat_ptr(data);
+ siginfo_t ssi;
+ siginfo_t __user *si = compat_alloc_user_space(sizeof(siginfo_t));
+ if (request == PTRACE_SETSIGINFO) {
+ memset(&ssi, 0, sizeof(siginfo_t));
+ ret = copy_siginfo_from_user32(&ssi, si32);
+ if (ret)
+ return ret;
+ if (copy_to_user(si, &ssi, sizeof(siginfo_t)))
+ return -EFAULT;
+ }
+ ret = sys_ptrace(request, pid, addr, (unsigned long)si);
+ if (ret)
+ return ret;
+ if (request == PTRACE_GETSIGINFO) {
+ if (copy_from_user(&ssi, si, sizeof(siginfo_t)))
+ return -EFAULT;
+ ret = copy_siginfo_to_user32(si32, &ssi);
+ }
+ return ret;
+}
+
+asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
+{
+ struct task_struct *child;
+ struct pt_regs *childregs;
+ void __user *datap = compat_ptr(data);
+ int ret;
+ __u32 val;
+
+ switch (request) {
+ case PTRACE_TRACEME:
+ case PTRACE_ATTACH:
+ case PTRACE_KILL:
+ case PTRACE_CONT:
+ case PTRACE_SINGLESTEP:
+ case PTRACE_DETACH:
+ case PTRACE_SYSCALL:
+ case PTRACE_OLDSETOPTIONS:
+ case PTRACE_SETOPTIONS:
+ case PTRACE_SET_THREAD_AREA:
+ case PTRACE_GET_THREAD_AREA:
+ return sys_ptrace(request, pid, addr, data);
+
+ default:
+ return -EINVAL;
+
+ case PTRACE_PEEKTEXT:
+ case PTRACE_PEEKDATA:
+ case PTRACE_POKEDATA:
+ case PTRACE_POKETEXT:
+ case PTRACE_POKEUSR:
+ case PTRACE_PEEKUSR:
+ case PTRACE_GETREGS:
+ case PTRACE_SETREGS:
+ case PTRACE_SETFPREGS:
+ case PTRACE_GETFPREGS:
+ case PTRACE_SETFPXREGS:
+ case PTRACE_GETFPXREGS:
+ case PTRACE_GETEVENTMSG:
+ break;
+
+ case PTRACE_SETSIGINFO:
+ case PTRACE_GETSIGINFO:
+ return ptrace32_siginfo(request, pid, addr, data);
+ }
+
+ child = ptrace_get_task_struct(pid);
+ if (IS_ERR(child))
+ return PTR_ERR(child);
+
+ ret = ptrace_check_attach(child, request == PTRACE_KILL);
+ if (ret < 0)
+ goto out;
+
+ childregs = task_pt_regs(child);
+
+ switch (request) {
+ case PTRACE_PEEKDATA:
+ case PTRACE_PEEKTEXT:
+ ret = 0;
+ if (access_process_vm(child, addr, &val, sizeof(u32), 0)!=sizeof(u32))
+ ret = -EIO;
+ else
+ ret = put_user(val, (unsigned int __user *)datap);
+ break;
+
+ case PTRACE_POKEDATA:
+ case PTRACE_POKETEXT:
+ ret = 0;
+ if (access_process_vm(child, addr, &data, sizeof(u32), 1)!=sizeof(u32))
+ ret = -EIO;
+ break;
+
+ case PTRACE_PEEKUSR:
+ ret = getreg32(child, addr, &val);
+ if (ret == 0)
+ ret = put_user(val, (__u32 __user *)datap);
+ break;
+
+ case PTRACE_POKEUSR:
+ ret = putreg32(child, addr, data);
+ break;
+
+ case PTRACE_GETREGS: { /* Get all gp regs from the child. */
+ int i;
+ if (!access_ok(VERIFY_WRITE, datap, 16*4)) {
+ ret = -EIO;
+ break;
+ }
+ ret = 0;
+ for ( i = 0; i <= 16*4 ; i += sizeof(__u32) ) {
+ getreg32(child, i, &val);
+ ret |= __put_user(val,(u32 __user *)datap);
+ datap += sizeof(u32);
+ }
+ break;
+ }
+
+ case PTRACE_SETREGS: { /* Set all gp regs in the child. */
+ unsigned long tmp;
+ int i;
+ if (!access_ok(VERIFY_READ, datap, 16*4)) {
+ ret = -EIO;
+ break;
+ }
+ ret = 0;
+ for ( i = 0; i <= 16*4; i += sizeof(u32) ) {
+ ret |= __get_user(tmp, (u32 __user *)datap);
+ putreg32(child, i, tmp);
+ datap += sizeof(u32);
+ }
+ break;
+ }
+
+ case PTRACE_GETFPREGS:
+ ret = -EIO;
+ if (!access_ok(VERIFY_READ, compat_ptr(data),
+ sizeof(struct user_i387_struct)))
+ break;
+ save_i387_ia32(child, datap, childregs, 1);
+ ret = 0;
+ break;
+
+ case PTRACE_SETFPREGS:
+ ret = -EIO;
+ if (!access_ok(VERIFY_WRITE, datap,
+ sizeof(struct user_i387_struct)))
+ break;
+ ret = 0;
+ /* don't check EFAULT to be bug-to-bug compatible to i386 */
+ restore_i387_ia32(child, datap, 1);
+ break;
+
+ case PTRACE_GETFPXREGS: {
+ struct user32_fxsr_struct __user *u = datap;
+ init_fpu(child);
+ ret = -EIO;
+ if (!access_ok(VERIFY_WRITE, u, sizeof(*u)))
+ break;
+ ret = -EFAULT;
+ if (__copy_to_user(u, &child->thread.i387.fxsave, sizeof(*u)))
+ break;
+ ret = __put_user(childregs->cs, &u->fcs);
+ ret |= __put_user(child->thread.ds, &u->fos);
+ break;
+ }
+ case PTRACE_SETFPXREGS: {
+ struct user32_fxsr_struct __user *u = datap;
+ unlazy_fpu(child);
+ ret = -EIO;
+ if (!access_ok(VERIFY_READ, u, sizeof(*u)))
+ break;
+ /* no checking to be bug-to-bug compatible with i386. */
+ /* but silence warning */
+ if (__copy_from_user(&child->thread.i387.fxsave, u, sizeof(*u)))
+ ;
+ set_stopped_child_used_math(child);
+ child->thread.i387.fxsave.mxcsr &= mxcsr_feature_mask;
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_GETEVENTMSG:
+ ret = put_user(child->ptrace_message,(unsigned int __user *)compat_ptr(data));
+ break;
+
+ default:
+ BUG();
+ }
+
+ out:
+ put_task_struct(child);
+ return ret;
+}
+
diff --git a/trunk/arch/x86/ia32/sys_ia32.c b/trunk/arch/x86/ia32/sys_ia32.c
index abf71d26fc2a..bee96d614432 100644
--- a/trunk/arch/x86/ia32/sys_ia32.c
+++ b/trunk/arch/x86/ia32/sys_ia32.c
@@ -1,29 +1,29 @@
/*
* sys_ia32.c: Conversion between 32bit and 64bit native syscalls. Based on
- * sys_sparc32
+ * sys_sparc32
*
* Copyright (C) 2000 VA Linux Co
* Copyright (C) 2000 Don Dugger
- * Copyright (C) 1999 Arun Sharma
- * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
- * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 1999 Arun Sharma
+ * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
* Copyright (C) 2000 Hewlett-Packard Co.
* Copyright (C) 2000 David Mosberger-Tang
- * Copyright (C) 2000,2001,2002 Andi Kleen, SuSE Labs (x86-64 port)
+ * Copyright (C) 2000,2001,2002 Andi Kleen, SuSE Labs (x86-64 port)
*
* These routines maintain argument size conversion between 32bit and 64bit
- * environment. In 2.5 most of this should be moved to a generic directory.
+ * environment. In 2.5 most of this should be moved to a generic directory.
*
* This file assumes that there is a hole at the end of user address space.
- *
- * Some of the functions are LE specific currently. These are
- * hopefully all marked. This should be fixed.
+ *
+ * Some of the functions are LE specific currently. These are hopefully all marked.
+ * This should be fixed.
*/
#include
#include
-#include
-#include
+#include
+#include
#include
#include
#include
@@ -90,44 +90,43 @@ int cp_compat_stat(struct kstat *kbuf, struct compat_stat __user *ubuf)
if (sizeof(ino) < sizeof(kbuf->ino) && ino != kbuf->ino)
return -EOVERFLOW;
if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct compat_stat)) ||
- __put_user(old_encode_dev(kbuf->dev), &ubuf->st_dev) ||
- __put_user(ino, &ubuf->st_ino) ||
- __put_user(kbuf->mode, &ubuf->st_mode) ||
- __put_user(kbuf->nlink, &ubuf->st_nlink) ||
- __put_user(uid, &ubuf->st_uid) ||
- __put_user(gid, &ubuf->st_gid) ||
- __put_user(old_encode_dev(kbuf->rdev), &ubuf->st_rdev) ||
- __put_user(kbuf->size, &ubuf->st_size) ||
- __put_user(kbuf->atime.tv_sec, &ubuf->st_atime) ||
- __put_user(kbuf->atime.tv_nsec, &ubuf->st_atime_nsec) ||
- __put_user(kbuf->mtime.tv_sec, &ubuf->st_mtime) ||
- __put_user(kbuf->mtime.tv_nsec, &ubuf->st_mtime_nsec) ||
- __put_user(kbuf->ctime.tv_sec, &ubuf->st_ctime) ||
- __put_user(kbuf->ctime.tv_nsec, &ubuf->st_ctime_nsec) ||
- __put_user(kbuf->blksize, &ubuf->st_blksize) ||
- __put_user(kbuf->blocks, &ubuf->st_blocks))
+ __put_user (old_encode_dev(kbuf->dev), &ubuf->st_dev) ||
+ __put_user (ino, &ubuf->st_ino) ||
+ __put_user (kbuf->mode, &ubuf->st_mode) ||
+ __put_user (kbuf->nlink, &ubuf->st_nlink) ||
+ __put_user (uid, &ubuf->st_uid) ||
+ __put_user (gid, &ubuf->st_gid) ||
+ __put_user (old_encode_dev(kbuf->rdev), &ubuf->st_rdev) ||
+ __put_user (kbuf->size, &ubuf->st_size) ||
+ __put_user (kbuf->atime.tv_sec, &ubuf->st_atime) ||
+ __put_user (kbuf->atime.tv_nsec, &ubuf->st_atime_nsec) ||
+ __put_user (kbuf->mtime.tv_sec, &ubuf->st_mtime) ||
+ __put_user (kbuf->mtime.tv_nsec, &ubuf->st_mtime_nsec) ||
+ __put_user (kbuf->ctime.tv_sec, &ubuf->st_ctime) ||
+ __put_user (kbuf->ctime.tv_nsec, &ubuf->st_ctime_nsec) ||
+ __put_user (kbuf->blksize, &ubuf->st_blksize) ||
+ __put_user (kbuf->blocks, &ubuf->st_blocks))
return -EFAULT;
return 0;
}
-asmlinkage long sys32_truncate64(char __user *filename,
- unsigned long offset_low,
- unsigned long offset_high)
+asmlinkage long
+sys32_truncate64(char __user * filename, unsigned long offset_low, unsigned long offset_high)
{
return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low);
}
-asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low,
- unsigned long offset_high)
+asmlinkage long
+sys32_ftruncate64(unsigned int fd, unsigned long offset_low, unsigned long offset_high)
{
return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low);
}
-/*
- * Another set for IA32/LFS -- x86_64 struct stat is different due to
- * support for 64bit inode numbers.
- */
-static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
+/* Another set for IA32/LFS -- x86_64 struct stat is different due to
+ support for 64bit inode numbers. */
+
+static int
+cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
{
typeof(ubuf->st_uid) uid = 0;
typeof(ubuf->st_gid) gid = 0;
@@ -135,39 +134,38 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
SET_GID(gid, stat->gid);
if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct stat64)) ||
__put_user(huge_encode_dev(stat->dev), &ubuf->st_dev) ||
- __put_user(stat->ino, &ubuf->__st_ino) ||
- __put_user(stat->ino, &ubuf->st_ino) ||
- __put_user(stat->mode, &ubuf->st_mode) ||
- __put_user(stat->nlink, &ubuf->st_nlink) ||
- __put_user(uid, &ubuf->st_uid) ||
- __put_user(gid, &ubuf->st_gid) ||
- __put_user(huge_encode_dev(stat->rdev), &ubuf->st_rdev) ||
- __put_user(stat->size, &ubuf->st_size) ||
- __put_user(stat->atime.tv_sec, &ubuf->st_atime) ||
- __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec) ||
- __put_user(stat->mtime.tv_sec, &ubuf->st_mtime) ||
- __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec) ||
- __put_user(stat->ctime.tv_sec, &ubuf->st_ctime) ||
- __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec) ||
- __put_user(stat->blksize, &ubuf->st_blksize) ||
- __put_user(stat->blocks, &ubuf->st_blocks))
+ __put_user (stat->ino, &ubuf->__st_ino) ||
+ __put_user (stat->ino, &ubuf->st_ino) ||
+ __put_user (stat->mode, &ubuf->st_mode) ||
+ __put_user (stat->nlink, &ubuf->st_nlink) ||
+ __put_user (uid, &ubuf->st_uid) ||
+ __put_user (gid, &ubuf->st_gid) ||
+ __put_user (huge_encode_dev(stat->rdev), &ubuf->st_rdev) ||
+ __put_user (stat->size, &ubuf->st_size) ||
+ __put_user (stat->atime.tv_sec, &ubuf->st_atime) ||
+ __put_user (stat->atime.tv_nsec, &ubuf->st_atime_nsec) ||
+ __put_user (stat->mtime.tv_sec, &ubuf->st_mtime) ||
+ __put_user (stat->mtime.tv_nsec, &ubuf->st_mtime_nsec) ||
+ __put_user (stat->ctime.tv_sec, &ubuf->st_ctime) ||
+ __put_user (stat->ctime.tv_nsec, &ubuf->st_ctime_nsec) ||
+ __put_user (stat->blksize, &ubuf->st_blksize) ||
+ __put_user (stat->blocks, &ubuf->st_blocks))
return -EFAULT;
return 0;
}
-asmlinkage long sys32_stat64(char __user *filename,
- struct stat64 __user *statbuf)
+asmlinkage long
+sys32_stat64(char __user * filename, struct stat64 __user *statbuf)
{
struct kstat stat;
int ret = vfs_stat(filename, &stat);
-
if (!ret)
ret = cp_stat64(statbuf, &stat);
return ret;
}
-asmlinkage long sys32_lstat64(char __user *filename,
- struct stat64 __user *statbuf)
+asmlinkage long
+sys32_lstat64(char __user * filename, struct stat64 __user *statbuf)
{
struct kstat stat;
int ret = vfs_lstat(filename, &stat);
@@ -176,7 +174,8 @@ asmlinkage long sys32_lstat64(char __user *filename,
return ret;
}
-asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
+asmlinkage long
+sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
{
struct kstat stat;
int ret = vfs_fstat(fd, &stat);
@@ -185,8 +184,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
return ret;
}
-asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename,
- struct stat64 __user *statbuf, int flag)
+asmlinkage long
+sys32_fstatat(unsigned int dfd, char __user *filename,
+ struct stat64 __user* statbuf, int flag)
{
struct kstat stat;
int error = -EINVAL;
@@ -221,7 +221,8 @@ struct mmap_arg_struct {
unsigned int offset;
};
-asmlinkage long sys32_mmap(struct mmap_arg_struct __user *arg)
+asmlinkage long
+sys32_mmap(struct mmap_arg_struct __user *arg)
{
struct mmap_arg_struct a;
struct file *file = NULL;
@@ -232,33 +233,33 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct __user *arg)
return -EFAULT;
if (a.offset & ~PAGE_MASK)
- return -EINVAL;
+ return -EINVAL;
if (!(a.flags & MAP_ANONYMOUS)) {
file = fget(a.fd);
if (!file)
return -EBADF;
}
-
- mm = current->mm;
- down_write(&mm->mmap_sem);
- retval = do_mmap_pgoff(file, a.addr, a.len, a.prot, a.flags,
- a.offset>>PAGE_SHIFT);
+
+ mm = current->mm;
+ down_write(&mm->mmap_sem);
+ retval = do_mmap_pgoff(file, a.addr, a.len, a.prot, a.flags, a.offset>>PAGE_SHIFT);
if (file)
fput(file);
- up_write(&mm->mmap_sem);
+ up_write(&mm->mmap_sem);
return retval;
}
-asmlinkage long sys32_mprotect(unsigned long start, size_t len,
- unsigned long prot)
+asmlinkage long
+sys32_mprotect(unsigned long start, size_t len, unsigned long prot)
{
- return sys_mprotect(start, len, prot);
+ return sys_mprotect(start,len,prot);
}
-asmlinkage long sys32_pipe(int __user *fd)
+asmlinkage long
+sys32_pipe(int __user *fd)
{
int retval;
int fds[2];
@@ -268,13 +269,13 @@ asmlinkage long sys32_pipe(int __user *fd)
goto out;
if (copy_to_user(fd, fds, sizeof(fds)))
retval = -EFAULT;
-out:
+ out:
return retval;
}
-asmlinkage long sys32_rt_sigaction(int sig, struct sigaction32 __user *act,
- struct sigaction32 __user *oact,
- unsigned int sigsetsize)
+asmlinkage long
+sys32_rt_sigaction(int sig, struct sigaction32 __user *act,
+ struct sigaction32 __user *oact, unsigned int sigsetsize)
{
struct k_sigaction new_ka, old_ka;
int ret;
@@ -290,17 +291,12 @@ asmlinkage long sys32_rt_sigaction(int sig, struct sigaction32 __user *act,
if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
__get_user(handler, &act->sa_handler) ||
__get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
- __get_user(restorer, &act->sa_restorer) ||
- __copy_from_user(&set32, &act->sa_mask,
- sizeof(compat_sigset_t)))
+ __get_user(restorer, &act->sa_restorer)||
+ __copy_from_user(&set32, &act->sa_mask, sizeof(compat_sigset_t)))
return -EFAULT;
new_ka.sa.sa_handler = compat_ptr(handler);
new_ka.sa.sa_restorer = compat_ptr(restorer);
-
- /*
- * FIXME: here we rely on _COMPAT_NSIG_WORS to be >=
- * than _NSIG_WORDS << 1
- */
+ /* FIXME: here we rely on _COMPAT_NSIG_WORS to be >= than _NSIG_WORDS << 1 */
switch (_NSIG_WORDS) {
case 4: new_ka.sa.sa_mask.sig[3] = set32.sig[6]
| (((long)set32.sig[7]) << 32);
@@ -316,10 +312,7 @@ asmlinkage long sys32_rt_sigaction(int sig, struct sigaction32 __user *act,
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
- /*
- * FIXME: here we rely on _COMPAT_NSIG_WORS to be >=
- * than _NSIG_WORDS << 1
- */
+ /* FIXME: here we rely on _COMPAT_NSIG_WORS to be >= than _NSIG_WORDS << 1 */
switch (_NSIG_WORDS) {
case 4:
set32.sig[7] = (old_ka.sa.sa_mask.sig[3] >> 32);
@@ -335,26 +328,23 @@ asmlinkage long sys32_rt_sigaction(int sig, struct sigaction32 __user *act,
set32.sig[0] = old_ka.sa.sa_mask.sig[0];
}
if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
- __put_user(ptr_to_compat(old_ka.sa.sa_handler),
- &oact->sa_handler) ||
- __put_user(ptr_to_compat(old_ka.sa.sa_restorer),
- &oact->sa_restorer) ||
+ __put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler) ||
+ __put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer) ||
__put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
- __copy_to_user(&oact->sa_mask, &set32,
- sizeof(compat_sigset_t)))
+ __copy_to_user(&oact->sa_mask, &set32, sizeof(compat_sigset_t)))
return -EFAULT;
}
return ret;
}
-asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act,
- struct old_sigaction32 __user *oact)
+asmlinkage long
+sys32_sigaction (int sig, struct old_sigaction32 __user *act, struct old_sigaction32 __user *oact)
{
- struct k_sigaction new_ka, old_ka;
- int ret;
+ struct k_sigaction new_ka, old_ka;
+ int ret;
- if (act) {
+ if (act) {
compat_old_sigset_t mask;
compat_uptr_t handler, restorer;
@@ -369,35 +359,33 @@ asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act,
new_ka.sa.sa_restorer = compat_ptr(restorer);
siginitset(&new_ka.sa.sa_mask, mask);
- }
+ }
- ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+ ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
- __put_user(ptr_to_compat(old_ka.sa.sa_handler),
- &oact->sa_handler) ||
- __put_user(ptr_to_compat(old_ka.sa.sa_restorer),
- &oact->sa_restorer) ||
+ __put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler) ||
+ __put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer) ||
__put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
return -EFAULT;
- }
+ }
return ret;
}
-asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
- compat_sigset_t __user *oset,
- unsigned int sigsetsize)
+asmlinkage long
+sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
+ compat_sigset_t __user *oset, unsigned int sigsetsize)
{
sigset_t s;
compat_sigset_t s32;
int ret;
mm_segment_t old_fs = get_fs();
-
+
if (set) {
- if (copy_from_user(&s32, set, sizeof(compat_sigset_t)))
+ if (copy_from_user (&s32, set, sizeof(compat_sigset_t)))
return -EFAULT;
switch (_NSIG_WORDS) {
case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32);
@@ -406,14 +394,13 @@ asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32);
}
}
- set_fs(KERNEL_DS);
+ set_fs (KERNEL_DS);
ret = sys_rt_sigprocmask(how,
set ? (sigset_t __user *)&s : NULL,
oset ? (sigset_t __user *)&s : NULL,
- sigsetsize);
- set_fs(old_fs);
- if (ret)
- return ret;
+ sigsetsize);
+ set_fs (old_fs);
+ if (ret) return ret;
if (oset) {
switch (_NSIG_WORDS) {
case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3];
@@ -421,49 +408,52 @@ asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1];
case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0];
}
- if (copy_to_user(oset, &s32, sizeof(compat_sigset_t)))
+ if (copy_to_user (oset, &s32, sizeof(compat_sigset_t)))
return -EFAULT;
}
return 0;
}
-static inline long get_tv32(struct timeval *o, struct compat_timeval __user *i)
+static inline long
+get_tv32(struct timeval *o, struct compat_timeval __user *i)
{
- int err = -EFAULT;
-
- if (access_ok(VERIFY_READ, i, sizeof(*i))) {
+ int err = -EFAULT;
+ if (access_ok(VERIFY_READ, i, sizeof(*i))) {
err = __get_user(o->tv_sec, &i->tv_sec);
err |= __get_user(o->tv_usec, &i->tv_usec);
}
- return err;
+ return err;
}
-static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i)
+static inline long
+put_tv32(struct compat_timeval __user *o, struct timeval *i)
{
int err = -EFAULT;
-
- if (access_ok(VERIFY_WRITE, o, sizeof(*o))) {
+ if (access_ok(VERIFY_WRITE, o, sizeof(*o))) {
err = __put_user(i->tv_sec, &o->tv_sec);
err |= __put_user(i->tv_usec, &o->tv_usec);
- }
- return err;
+ }
+ return err;
}
-asmlinkage long sys32_alarm(unsigned int seconds)
+extern unsigned int alarm_setitimer(unsigned int seconds);
+
+asmlinkage long
+sys32_alarm(unsigned int seconds)
{
return alarm_setitimer(seconds);
}
-/*
- * Translations due to time_t size differences. Which affects all
- * sorts of things, like timeval and itimerval.
- */
-asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv,
- struct timezone __user *tz)
+/* Translations due to time_t size differences. Which affects all
+ sorts of things, like timeval and itimerval. */
+
+extern struct timezone sys_tz;
+
+asmlinkage long
+sys32_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz)
{
if (tv) {
struct timeval ktv;
-
do_gettimeofday(&ktv);
if (put_tv32(tv, &ktv))
return -EFAULT;
@@ -475,14 +465,14 @@ asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv,
return 0;
}
-asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv,
- struct timezone __user *tz)
+asmlinkage long
+sys32_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz)
{
struct timeval ktv;
struct timespec kts;
struct timezone ktz;
- if (tv) {
+ if (tv) {
if (get_tv32(&ktv, tv))
return -EFAULT;
kts.tv_sec = ktv.tv_sec;
@@ -504,7 +494,8 @@ struct sel_arg_struct {
unsigned int tvp;
};
-asmlinkage long sys32_old_select(struct sel_arg_struct __user *arg)
+asmlinkage long
+sys32_old_select(struct sel_arg_struct __user *arg)
{
struct sel_arg_struct a;
@@ -514,45 +505,50 @@ asmlinkage long sys32_old_select(struct sel_arg_struct __user *arg)
compat_ptr(a.exp), compat_ptr(a.tvp));
}
-asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr,
- int options)
+extern asmlinkage long
+compat_sys_wait4(compat_pid_t pid, compat_uint_t * stat_addr, int options,
+ struct compat_rusage *ru);
+
+asmlinkage long
+sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr, int options)
{
return compat_sys_wait4(pid, stat_addr, options, NULL);
}
/* 32-bit timeval and related flotsam. */
-asmlinkage long sys32_sysfs(int option, u32 arg1, u32 arg2)
+asmlinkage long
+sys32_sysfs(int option, u32 arg1, u32 arg2)
{
return sys_sysfs(option, arg1, arg2);
}
-asmlinkage long sys32_sched_rr_get_interval(compat_pid_t pid,
- struct compat_timespec __user *interval)
+asmlinkage long
+sys32_sched_rr_get_interval(compat_pid_t pid, struct compat_timespec __user *interval)
{
struct timespec t;
int ret;
- mm_segment_t old_fs = get_fs();
-
- set_fs(KERNEL_DS);
+ mm_segment_t old_fs = get_fs ();
+
+ set_fs (KERNEL_DS);
ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t);
- set_fs(old_fs);
+ set_fs (old_fs);
if (put_compat_timespec(&t, interval))
return -EFAULT;
return ret;
}
-asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set,
- compat_size_t sigsetsize)
+asmlinkage long
+sys32_rt_sigpending(compat_sigset_t __user *set, compat_size_t sigsetsize)
{
sigset_t s;
compat_sigset_t s32;
int ret;
mm_segment_t old_fs = get_fs();
-
- set_fs(KERNEL_DS);
+
+ set_fs (KERNEL_DS);
ret = sys_rt_sigpending((sigset_t __user *)&s, sigsetsize);
- set_fs(old_fs);
+ set_fs (old_fs);
if (!ret) {
switch (_NSIG_WORDS) {
case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3];
@@ -560,29 +556,30 @@ asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set,
case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1];
case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0];
}
- if (copy_to_user(set, &s32, sizeof(compat_sigset_t)))
+ if (copy_to_user (set, &s32, sizeof(compat_sigset_t)))
return -EFAULT;
}
return ret;
}
-asmlinkage long sys32_rt_sigqueueinfo(int pid, int sig,
- compat_siginfo_t __user *uinfo)
+asmlinkage long
+sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo)
{
siginfo_t info;
int ret;
mm_segment_t old_fs = get_fs();
-
+
if (copy_siginfo_from_user32(&info, uinfo))
return -EFAULT;
- set_fs(KERNEL_DS);
+ set_fs (KERNEL_DS);
ret = sys_rt_sigqueueinfo(pid, sig, (siginfo_t __user *)&info);
- set_fs(old_fs);
+ set_fs (old_fs);
return ret;
}
/* These are here just in case some old ia32 binary calls it. */
-asmlinkage long sys32_pause(void)
+asmlinkage long
+sys32_pause(void)
{
current->state = TASK_INTERRUPTIBLE;
schedule();
@@ -602,25 +599,25 @@ struct sysctl_ia32 {
};
-asmlinkage long sys32_sysctl(struct sysctl_ia32 __user *args32)
+asmlinkage long
+sys32_sysctl(struct sysctl_ia32 __user *args32)
{
struct sysctl_ia32 a32;
- mm_segment_t old_fs = get_fs();
+ mm_segment_t old_fs = get_fs ();
void __user *oldvalp, *newvalp;
size_t oldlen;
int __user *namep;
long ret;
- if (copy_from_user(&a32, args32, sizeof(a32)))
+ if (copy_from_user(&a32, args32, sizeof (a32)))
return -EFAULT;
/*
- * We need to pre-validate these because we have to disable
- * address checking before calling do_sysctl() because of
- * OLDLEN but we can't run the risk of the user specifying bad
- * addresses here. Well, since we're dealing with 32 bit
- * addresses, we KNOW that access_ok() will always succeed, so
- * this is an expensive NOP, but so what...
+ * We need to pre-validate these because we have to disable address checking
+ * before calling do_sysctl() because of OLDLEN but we can't run the risk of the
+ * user specifying bad addresses here. Well, since we're dealing with 32 bit
+ * addresses, we KNOW that access_ok() will always succeed, so this is an
+ * expensive NOP, but so what...
*/
namep = compat_ptr(a32.name);
oldvalp = compat_ptr(a32.oldval);
@@ -639,34 +636,34 @@ asmlinkage long sys32_sysctl(struct sysctl_ia32 __user *args32)
unlock_kernel();
set_fs(old_fs);
- if (oldvalp && put_user(oldlen, (int __user *)compat_ptr(a32.oldlenp)))
+ if (oldvalp && put_user (oldlen, (int __user *)compat_ptr(a32.oldlenp)))
return -EFAULT;
return ret;
}
#endif
-/* warning: next two assume little endian */
-asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count,
- u32 poslo, u32 poshi)
+/* warning: next two assume little endian */
+asmlinkage long
+sys32_pread(unsigned int fd, char __user *ubuf, u32 count, u32 poslo, u32 poshi)
{
return sys_pread64(fd, ubuf, count,
((loff_t)AA(poshi) << 32) | AA(poslo));
}
-asmlinkage long sys32_pwrite(unsigned int fd, char __user *ubuf, u32 count,
- u32 poslo, u32 poshi)
+asmlinkage long
+sys32_pwrite(unsigned int fd, char __user *ubuf, u32 count, u32 poslo, u32 poshi)
{
return sys_pwrite64(fd, ubuf, count,
((loff_t)AA(poshi) << 32) | AA(poslo));
}
-asmlinkage long sys32_personality(unsigned long personality)
+asmlinkage long
+sys32_personality(unsigned long personality)
{
int ret;
-
- if (personality(current->personality) == PER_LINUX32 &&
+ if (personality(current->personality) == PER_LINUX32 &&
personality == PER_LINUX)
personality = PER_LINUX32;
ret = sys_personality(personality);
@@ -675,33 +672,34 @@ asmlinkage long sys32_personality(unsigned long personality)
return ret;
}
-asmlinkage long sys32_sendfile(int out_fd, int in_fd,
- compat_off_t __user *offset, s32 count)
+asmlinkage long
+sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, s32 count)
{
mm_segment_t old_fs = get_fs();
int ret;
off_t of;
-
+
if (offset && get_user(of, offset))
return -EFAULT;
-
+
set_fs(KERNEL_DS);
ret = sys_sendfile(out_fd, in_fd, offset ? (off_t __user *)&of : NULL,
count);
set_fs(old_fs);
-
+
if (offset && put_user(of, offset))
return -EFAULT;
+
return ret;
}
asmlinkage long sys32_mmap2(unsigned long addr, unsigned long len,
- unsigned long prot, unsigned long flags,
- unsigned long fd, unsigned long pgoff)
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
{
struct mm_struct *mm = current->mm;
unsigned long error;
- struct file *file = NULL;
+ struct file * file = NULL;
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
if (!(flags & MAP_ANONYMOUS)) {
@@ -719,35 +717,36 @@ asmlinkage long sys32_mmap2(unsigned long addr, unsigned long len,
return error;
}
-asmlinkage long sys32_olduname(struct oldold_utsname __user *name)
+asmlinkage long sys32_olduname(struct oldold_utsname __user * name)
{
- char *arch = "x86_64";
int err;
if (!name)
return -EFAULT;
if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname)))
return -EFAULT;
-
- down_read(&uts_sem);
-
- err = __copy_to_user(&name->sysname, &utsname()->sysname,
- __OLD_UTS_LEN);
- err |= __put_user(0, name->sysname+__OLD_UTS_LEN);
- err |= __copy_to_user(&name->nodename, &utsname()->nodename,
- __OLD_UTS_LEN);
- err |= __put_user(0, name->nodename+__OLD_UTS_LEN);
- err |= __copy_to_user(&name->release, &utsname()->release,
- __OLD_UTS_LEN);
- err |= __put_user(0, name->release+__OLD_UTS_LEN);
- err |= __copy_to_user(&name->version, &utsname()->version,
- __OLD_UTS_LEN);
- err |= __put_user(0, name->version+__OLD_UTS_LEN);
-
- if (personality(current->personality) == PER_LINUX32)
- arch = "i686";
-
- err |= __copy_to_user(&name->machine, arch, strlen(arch) + 1);
+
+ down_read(&uts_sem);
+
+ err = __copy_to_user(&name->sysname,&utsname()->sysname,
+ __OLD_UTS_LEN);
+ err |= __put_user(0,name->sysname+__OLD_UTS_LEN);
+ err |= __copy_to_user(&name->nodename,&utsname()->nodename,
+ __OLD_UTS_LEN);
+ err |= __put_user(0,name->nodename+__OLD_UTS_LEN);
+ err |= __copy_to_user(&name->release,&utsname()->release,
+ __OLD_UTS_LEN);
+ err |= __put_user(0,name->release+__OLD_UTS_LEN);
+ err |= __copy_to_user(&name->version,&utsname()->version,
+ __OLD_UTS_LEN);
+ err |= __put_user(0,name->version+__OLD_UTS_LEN);
+ {
+ char *arch = "x86_64";
+ if (personality(current->personality) == PER_LINUX32)
+ arch = "i686";
+
+ err |= __copy_to_user(&name->machine, arch, strlen(arch)+1);
+ }
up_read(&uts_sem);
@@ -756,19 +755,17 @@ asmlinkage long sys32_olduname(struct oldold_utsname __user *name)
return err;
}
-long sys32_uname(struct old_utsname __user *name)
+long sys32_uname(struct old_utsname __user * name)
{
int err;
-
if (!name)
return -EFAULT;
down_read(&uts_sem);
- err = copy_to_user(name, utsname(), sizeof(*name));
+ err = copy_to_user(name, utsname(), sizeof (*name));
up_read(&uts_sem);
- if (personality(current->personality) == PER_LINUX32)
+ if (personality(current->personality) == PER_LINUX32)
err |= copy_to_user(&name->machine, "i686", 5);
-
- return err ? -EFAULT : 0;
+ return err?-EFAULT:0;
}
long sys32_ustat(unsigned dev, struct ustat32 __user *u32p)
@@ -776,28 +773,27 @@ long sys32_ustat(unsigned dev, struct ustat32 __user *u32p)
struct ustat u;
mm_segment_t seg;
int ret;
-
- seg = get_fs();
- set_fs(KERNEL_DS);
+
+ seg = get_fs();
+ set_fs(KERNEL_DS);
ret = sys_ustat(dev, (struct ustat __user *)&u);
set_fs(seg);
- if (ret < 0)
- return ret;
-
- if (!access_ok(VERIFY_WRITE, u32p, sizeof(struct ustat32)) ||
- __put_user((__u32) u.f_tfree, &u32p->f_tfree) ||
- __put_user((__u32) u.f_tinode, &u32p->f_tfree) ||
- __copy_to_user(&u32p->f_fname, u.f_fname, sizeof(u.f_fname)) ||
- __copy_to_user(&u32p->f_fpack, u.f_fpack, sizeof(u.f_fpack)))
- ret = -EFAULT;
+ if (ret >= 0) {
+ if (!access_ok(VERIFY_WRITE,u32p,sizeof(struct ustat32)) ||
+ __put_user((__u32) u.f_tfree, &u32p->f_tfree) ||
+ __put_user((__u32) u.f_tinode, &u32p->f_tfree) ||
+ __copy_to_user(&u32p->f_fname, u.f_fname, sizeof(u.f_fname)) ||
+ __copy_to_user(&u32p->f_fpack, u.f_fpack, sizeof(u.f_fpack)))
+ ret = -EFAULT;
+ }
return ret;
-}
+}
asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv,
compat_uptr_t __user *envp, struct pt_regs *regs)
{
long error;
- char *filename;
+ char * filename;
filename = getname(name);
error = PTR_ERR(filename);
@@ -816,19 +812,18 @@ asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv,
asmlinkage long sys32_clone(unsigned int clone_flags, unsigned int newsp,
struct pt_regs *regs)
{
- void __user *parent_tid = (void __user *)regs->dx;
- void __user *child_tid = (void __user *)regs->di;
-
+ void __user *parent_tid = (void __user *)regs->rdx;
+ void __user *child_tid = (void __user *)regs->rdi;
if (!newsp)
- newsp = regs->sp;
- return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
+ newsp = regs->rsp;
+ return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
}
/*
- * Some system calls that need sign extended arguments. This could be
- * done by a generic wrapper.
- */
-long sys32_lseek(unsigned int fd, int offset, unsigned int whence)
+ * Some system calls that need sign extended arguments. This could be done by a generic wrapper.
+ */
+
+long sys32_lseek (unsigned int fd, int offset, unsigned int whence)
{
return sys_lseek(fd, offset, whence);
}
@@ -837,52 +832,49 @@ long sys32_kill(int pid, int sig)
{
return sys_kill(pid, sig);
}
-
-long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
+
+long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
__u32 len_low, __u32 len_high, int advice)
-{
+{
return sys_fadvise64_64(fd,
(((u64)offset_high)<<32) | offset_low,
(((u64)len_high)<<32) | len_low,
- advice);
-}
+ advice);
+}
long sys32_vm86_warning(void)
-{
+{
struct task_struct *me = current;
static char lastcomm[sizeof(me->comm)];
-
if (strncmp(lastcomm, me->comm, sizeof(lastcomm))) {
- compat_printk(KERN_INFO
- "%s: vm86 mode not supported on 64 bit kernel\n",
- me->comm);
+ compat_printk(KERN_INFO "%s: vm86 mode not supported on 64 bit kernel\n",
+ me->comm);
strncpy(lastcomm, me->comm, sizeof(lastcomm));
- }
+ }
return -ENOSYS;
-}
+}
long sys32_lookup_dcookie(u32 addr_low, u32 addr_high,
- char __user *buf, size_t len)
+ char __user * buf, size_t len)
{
return sys_lookup_dcookie(((u64)addr_high << 32) | addr_low, buf, len);
}
-asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi,
- size_t count)
+asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi, size_t count)
{
return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count);
}
asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi,
- unsigned n_low, unsigned n_hi, int flags)
+ unsigned n_low, unsigned n_hi, int flags)
{
return sys_sync_file_range(fd,
((u64)off_hi << 32) | off_low,
((u64)n_hi << 32) | n_low, flags);
}
-asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi,
- size_t len, int advice)
+asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi, size_t len,
+ int advice)
{
return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
len, advice);
diff --git a/trunk/arch/x86/ia32/syscall32.c b/trunk/arch/x86/ia32/syscall32.c
new file mode 100644
index 000000000000..15013bac181c
--- /dev/null
+++ b/trunk/arch/x86/ia32/syscall32.c
@@ -0,0 +1,83 @@
+/* Copyright 2002,2003 Andi Kleen, SuSE Labs */
+
+/* vsyscall handling for 32bit processes. Map a stub page into it
+ on demand because 32bit cannot reach the kernel's fixmaps */
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+extern unsigned char syscall32_syscall[], syscall32_syscall_end[];
+extern unsigned char syscall32_sysenter[], syscall32_sysenter_end[];
+extern int sysctl_vsyscall32;
+
+static struct page *syscall32_pages[1];
+static int use_sysenter = -1;
+
+struct linux_binprm;
+
+/* Setup a VMA at program startup for the vsyscall page */
+int syscall32_setup_pages(struct linux_binprm *bprm, int exstack)
+{
+ struct mm_struct *mm = current->mm;
+ int ret;
+
+ down_write(&mm->mmap_sem);
+ /*
+ * MAYWRITE to allow gdb to COW and set breakpoints
+ *
+ * Make sure the vDSO gets into every core dump.
+ * Dumping its contents makes post-mortem fully interpretable later
+ * without matching up the same kernel and hardware config to see
+ * what PC values meant.
+ */
+ /* Could randomize here */
+ ret = install_special_mapping(mm, VSYSCALL32_BASE, PAGE_SIZE,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+ VM_ALWAYSDUMP,
+ syscall32_pages);
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+static int __init init_syscall32(void)
+{
+ char *syscall32_page = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!syscall32_page)
+ panic("Cannot allocate syscall32 page");
+ syscall32_pages[0] = virt_to_page(syscall32_page);
+ if (use_sysenter > 0) {
+ memcpy(syscall32_page, syscall32_sysenter,
+ syscall32_sysenter_end - syscall32_sysenter);
+ } else {
+ memcpy(syscall32_page, syscall32_syscall,
+ syscall32_syscall_end - syscall32_syscall);
+ }
+ return 0;
+}
+
+__initcall(init_syscall32);
+
+/* May not be __init: called during resume */
+void syscall32_cpu_init(void)
+{
+ if (use_sysenter < 0)
+ use_sysenter = (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL);
+
+ /* Load these always in case some future AMD CPU supports
+ SYSENTER from compat mode too. */
+ checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+ checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL);
+ checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+
+ wrmsrl(MSR_CSTAR, ia32_cstar_target);
+}
diff --git a/trunk/arch/x86/ia32/syscall32_syscall.S b/trunk/arch/x86/ia32/syscall32_syscall.S
new file mode 100644
index 000000000000..933f0f08b1cf
--- /dev/null
+++ b/trunk/arch/x86/ia32/syscall32_syscall.S
@@ -0,0 +1,17 @@
+/* 32bit VDSOs mapped into user space. */
+
+ .section ".init.data","aw"
+
+ .globl syscall32_syscall
+ .globl syscall32_syscall_end
+
+syscall32_syscall:
+ .incbin "arch/x86/ia32/vsyscall-syscall.so"
+syscall32_syscall_end:
+
+ .globl syscall32_sysenter
+ .globl syscall32_sysenter_end
+
+syscall32_sysenter:
+ .incbin "arch/x86/ia32/vsyscall-sysenter.so"
+syscall32_sysenter_end:
diff --git a/trunk/arch/x86/ia32/tls32.c b/trunk/arch/x86/ia32/tls32.c
new file mode 100644
index 000000000000..1cc4340de3ca
--- /dev/null
+++ b/trunk/arch/x86/ia32/tls32.c
@@ -0,0 +1,163 @@
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+#include
+#include
+#include
+
+/*
+ * sys_alloc_thread_area: get a yet unused TLS descriptor index.
+ */
+static int get_free_idx(void)
+{
+ struct thread_struct *t = ¤t->thread;
+ int idx;
+
+ for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++)
+ if (desc_empty((struct n_desc_struct *)(t->tls_array) + idx))
+ return idx + GDT_ENTRY_TLS_MIN;
+ return -ESRCH;
+}
+
+/*
+ * Set a given TLS descriptor:
+ * When you want addresses > 32bit use arch_prctl()
+ */
+int do_set_thread_area(struct thread_struct *t, struct user_desc __user *u_info)
+{
+ struct user_desc info;
+ struct n_desc_struct *desc;
+ int cpu, idx;
+
+ if (copy_from_user(&info, u_info, sizeof(info)))
+ return -EFAULT;
+
+ idx = info.entry_number;
+
+ /*
+ * index -1 means the kernel should try to find and
+ * allocate an empty descriptor:
+ */
+ if (idx == -1) {
+ idx = get_free_idx();
+ if (idx < 0)
+ return idx;
+ if (put_user(idx, &u_info->entry_number))
+ return -EFAULT;
+ }
+
+ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+ return -EINVAL;
+
+ desc = ((struct n_desc_struct *)t->tls_array) + idx - GDT_ENTRY_TLS_MIN;
+
+ /*
+ * We must not get preempted while modifying the TLS.
+ */
+ cpu = get_cpu();
+
+ if (LDT_empty(&info)) {
+ desc->a = 0;
+ desc->b = 0;
+ } else {
+ desc->a = LDT_entry_a(&info);
+ desc->b = LDT_entry_b(&info);
+ }
+ if (t == ¤t->thread)
+ load_TLS(t, cpu);
+
+ put_cpu();
+ return 0;
+}
+
+asmlinkage long sys32_set_thread_area(struct user_desc __user *u_info)
+{
+ return do_set_thread_area(¤t->thread, u_info);
+}
+
+
+/*
+ * Get the current Thread-Local Storage area:
+ */
+
+#define GET_BASE(desc) ( \
+ (((desc)->a >> 16) & 0x0000ffff) | \
+ (((desc)->b << 16) & 0x00ff0000) | \
+ ( (desc)->b & 0xff000000) )
+
+#define GET_LIMIT(desc) ( \
+ ((desc)->a & 0x0ffff) | \
+ ((desc)->b & 0xf0000) )
+
+#define GET_32BIT(desc) (((desc)->b >> 22) & 1)
+#define GET_CONTENTS(desc) (((desc)->b >> 10) & 3)
+#define GET_WRITABLE(desc) (((desc)->b >> 9) & 1)
+#define GET_LIMIT_PAGES(desc) (((desc)->b >> 23) & 1)
+#define GET_PRESENT(desc) (((desc)->b >> 15) & 1)
+#define GET_USEABLE(desc) (((desc)->b >> 20) & 1)
+#define GET_LONGMODE(desc) (((desc)->b >> 21) & 1)
+
+int do_get_thread_area(struct thread_struct *t, struct user_desc __user *u_info)
+{
+ struct user_desc info;
+ struct n_desc_struct *desc;
+ int idx;
+
+ if (get_user(idx, &u_info->entry_number))
+ return -EFAULT;
+ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+ return -EINVAL;
+
+ desc = ((struct n_desc_struct *)t->tls_array) + idx - GDT_ENTRY_TLS_MIN;
+
+ memset(&info, 0, sizeof(struct user_desc));
+ info.entry_number = idx;
+ info.base_addr = GET_BASE(desc);
+ info.limit = GET_LIMIT(desc);
+ info.seg_32bit = GET_32BIT(desc);
+ info.contents = GET_CONTENTS(desc);
+ info.read_exec_only = !GET_WRITABLE(desc);
+ info.limit_in_pages = GET_LIMIT_PAGES(desc);
+ info.seg_not_present = !GET_PRESENT(desc);
+ info.useable = GET_USEABLE(desc);
+ info.lm = GET_LONGMODE(desc);
+
+ if (copy_to_user(u_info, &info, sizeof(info)))
+ return -EFAULT;
+ return 0;
+}
+
+asmlinkage long sys32_get_thread_area(struct user_desc __user *u_info)
+{
+ return do_get_thread_area(¤t->thread, u_info);
+}
+
+
+int ia32_child_tls(struct task_struct *p, struct pt_regs *childregs)
+{
+ struct n_desc_struct *desc;
+ struct user_desc info;
+ struct user_desc __user *cp;
+ int idx;
+
+ cp = (void __user *)childregs->rsi;
+ if (copy_from_user(&info, cp, sizeof(info)))
+ return -EFAULT;
+ if (LDT_empty(&info))
+ return -EINVAL;
+
+ idx = info.entry_number;
+ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+ return -EINVAL;
+
+ desc = (struct n_desc_struct *)(p->thread.tls_array) + idx - GDT_ENTRY_TLS_MIN;
+ desc->a = LDT_entry_a(&info);
+ desc->b = LDT_entry_b(&info);
+
+ return 0;
+}
diff --git a/trunk/arch/x86/ia32/vsyscall-sigreturn.S b/trunk/arch/x86/ia32/vsyscall-sigreturn.S
new file mode 100644
index 000000000000..b383be00baec
--- /dev/null
+++ b/trunk/arch/x86/ia32/vsyscall-sigreturn.S
@@ -0,0 +1,143 @@
+/*
+ * Common code for the sigreturn entry points on the vsyscall page.
+ * This code uses SYSCALL_ENTER_KERNEL (either syscall or int $0x80)
+ * to enter the kernel.
+ * This file is #include'd by vsyscall-*.S to define them after the
+ * vsyscall entry point. The addresses we get for these entry points
+ * by doing ".balign 32" must match in both versions of the page.
+ */
+
+ .code32
+ .section .text.sigreturn,"ax"
+ .balign 32
+ .globl __kernel_sigreturn
+ .type __kernel_sigreturn,@function
+__kernel_sigreturn:
+.LSTART_sigreturn:
+ popl %eax
+ movl $__NR_ia32_sigreturn, %eax
+ SYSCALL_ENTER_KERNEL
+.LEND_sigreturn:
+ .size __kernel_sigreturn,.-.LSTART_sigreturn
+
+ .section .text.rtsigreturn,"ax"
+ .balign 32
+ .globl __kernel_rt_sigreturn
+ .type __kernel_rt_sigreturn,@function
+__kernel_rt_sigreturn:
+.LSTART_rt_sigreturn:
+ movl $__NR_ia32_rt_sigreturn, %eax
+ SYSCALL_ENTER_KERNEL
+.LEND_rt_sigreturn:
+ .size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn
+
+ .section .eh_frame,"a",@progbits
+.LSTARTFRAMES:
+ .long .LENDCIES-.LSTARTCIES
+.LSTARTCIES:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zRS" /* NUL-terminated augmentation string */
+ .uleb128 1 /* Code alignment factor */
+ .sleb128 -4 /* Data alignment factor */
+ .byte 8 /* Return address register column */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+ .byte 0x0c /* DW_CFA_def_cfa */
+ .uleb128 4
+ .uleb128 4
+ .byte 0x88 /* DW_CFA_offset, column 0x8 */
+ .uleb128 1
+ .align 4
+.LENDCIES:
+
+ .long .LENDFDE2-.LSTARTFDE2 /* Length FDE */
+.LSTARTFDE2:
+ .long .LSTARTFDE2-.LSTARTFRAMES /* CIE pointer */
+ /* HACK: The dwarf2 unwind routines will subtract 1 from the
+ return address to get an address in the middle of the
+ presumed call instruction. Since we didn't get here via
+ a call, we need to include the nop before the real start
+ to make up for it. */
+ .long .LSTART_sigreturn-1-. /* PC-relative start address */
+ .long .LEND_sigreturn-.LSTART_sigreturn+1
+ .uleb128 0 /* Augmentation length */
+ /* What follows are the instructions for the table generation.
+ We record the locations of each register saved. This is
+ complicated by the fact that the "CFA" is always assumed to
+ be the value of the stack pointer in the caller. This means
+ that we must define the CFA of this body of code to be the
+ saved value of the stack pointer in the sigcontext. Which
+ also means that there is no fixed relation to the other
+ saved registers, which means that we must use DW_CFA_expression
+ to compute their addresses. It also means that when we
+ adjust the stack with the popl, we have to do it all over again. */
+
+#define do_cfa_expr(offset) \
+ .byte 0x0f; /* DW_CFA_def_cfa_expression */ \
+ .uleb128 1f-0f; /* length */ \
+0: .byte 0x74; /* DW_OP_breg4 */ \
+ .sleb128 offset; /* offset */ \
+ .byte 0x06; /* DW_OP_deref */ \
+1:
+
+#define do_expr(regno, offset) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno; /* regno */ \
+ .uleb128 1f-0f; /* length */ \
+0: .byte 0x74; /* DW_OP_breg4 */ \
+ .sleb128 offset; /* offset */ \
+1:
+
+ do_cfa_expr(IA32_SIGCONTEXT_esp+4)
+ do_expr(0, IA32_SIGCONTEXT_eax+4)
+ do_expr(1, IA32_SIGCONTEXT_ecx+4)
+ do_expr(2, IA32_SIGCONTEXT_edx+4)
+ do_expr(3, IA32_SIGCONTEXT_ebx+4)
+ do_expr(5, IA32_SIGCONTEXT_ebp+4)
+ do_expr(6, IA32_SIGCONTEXT_esi+4)
+ do_expr(7, IA32_SIGCONTEXT_edi+4)
+ do_expr(8, IA32_SIGCONTEXT_eip+4)
+
+ .byte 0x42 /* DW_CFA_advance_loc 2 -- nop; popl eax. */
+
+ do_cfa_expr(IA32_SIGCONTEXT_esp)
+ do_expr(0, IA32_SIGCONTEXT_eax)
+ do_expr(1, IA32_SIGCONTEXT_ecx)
+ do_expr(2, IA32_SIGCONTEXT_edx)
+ do_expr(3, IA32_SIGCONTEXT_ebx)
+ do_expr(5, IA32_SIGCONTEXT_ebp)
+ do_expr(6, IA32_SIGCONTEXT_esi)
+ do_expr(7, IA32_SIGCONTEXT_edi)
+ do_expr(8, IA32_SIGCONTEXT_eip)
+
+ .align 4
+.LENDFDE2:
+
+ .long .LENDFDE3-.LSTARTFDE3 /* Length FDE */
+.LSTARTFDE3:
+ .long .LSTARTFDE3-.LSTARTFRAMES /* CIE pointer */
+ /* HACK: See above wrt unwind library assumptions. */
+ .long .LSTART_rt_sigreturn-1-. /* PC-relative start address */
+ .long .LEND_rt_sigreturn-.LSTART_rt_sigreturn+1
+ .uleb128 0 /* Augmentation */
+ /* What follows are the instructions for the table generation.
+ We record the locations of each register saved. This is
+ slightly less complicated than the above, since we don't
+ modify the stack pointer in the process. */
+
+ do_cfa_expr(IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_esp)
+ do_expr(0, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_eax)
+ do_expr(1, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ecx)
+ do_expr(2, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_edx)
+ do_expr(3, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ebx)
+ do_expr(5, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ebp)
+ do_expr(6, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_esi)
+ do_expr(7, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_edi)
+ do_expr(8, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_eip)
+
+ .align 4
+.LENDFDE3:
+
+#include "../../x86/kernel/vsyscall-note_32.S"
+
diff --git a/trunk/arch/x86/vdso/vdso32/syscall.S b/trunk/arch/x86/ia32/vsyscall-syscall.S
similarity index 79%
rename from trunk/arch/x86/vdso/vdso32/syscall.S
rename to trunk/arch/x86/ia32/vsyscall-syscall.S
index 5415b5613d55..cf9ef678de3e 100644
--- a/trunk/arch/x86/vdso/vdso32/syscall.S
+++ b/trunk/arch/x86/ia32/vsyscall-syscall.S
@@ -1,18 +1,16 @@
/*
- * Code for the vDSO. This version uses the syscall instruction.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
+ * Code for the vsyscall page. This version uses the syscall instruction.
*/
-#define SYSCALL_ENTER_KERNEL syscall
-#include "sigreturn.S"
+#include
+#include
#include
+ .code32
.text
+ .section .text.vsyscall,"ax"
.globl __kernel_vsyscall
.type __kernel_vsyscall,@function
- ALIGN
__kernel_vsyscall:
.LSTART_vsyscall:
push %ebp
@@ -66,12 +64,6 @@ __kernel_vsyscall:
.uleb128 4
.align 4
.LENDFDE1:
- .previous
- /*
- * Pad out the segment to match the size of the sysenter.S version.
- */
-VDSO32_vsyscall_eh_frame_size = 0x40
- .section .data,"aw",@progbits
- .space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0
- .previous
+#define SYSCALL_ENTER_KERNEL syscall
+#include "vsyscall-sigreturn.S"
diff --git a/trunk/arch/x86/ia32/vsyscall-sysenter.S b/trunk/arch/x86/ia32/vsyscall-sysenter.S
new file mode 100644
index 000000000000..ae056e553d13
--- /dev/null
+++ b/trunk/arch/x86/ia32/vsyscall-sysenter.S
@@ -0,0 +1,95 @@
+/*
+ * Code for the vsyscall page. This version uses the sysenter instruction.
+ */
+
+#include
+#include
+
+ .code32
+ .text
+ .section .text.vsyscall,"ax"
+ .globl __kernel_vsyscall
+ .type __kernel_vsyscall,@function
+__kernel_vsyscall:
+.LSTART_vsyscall:
+ push %ecx
+.Lpush_ecx:
+ push %edx
+.Lpush_edx:
+ push %ebp
+.Lenter_kernel:
+ movl %esp,%ebp
+ sysenter
+ .space 7,0x90
+ jmp .Lenter_kernel
+ /* 16: System call normal return point is here! */
+ pop %ebp
+.Lpop_ebp:
+ pop %edx
+.Lpop_edx:
+ pop %ecx
+.Lpop_ecx:
+ ret
+.LEND_vsyscall:
+ .size __kernel_vsyscall,.-.LSTART_vsyscall
+
+ .section .eh_frame,"a",@progbits
+.LSTARTFRAME:
+ .long .LENDCIE-.LSTARTCIE
+.LSTARTCIE:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zR" /* NUL-terminated augmentation string */
+ .uleb128 1 /* Code alignment factor */
+ .sleb128 -4 /* Data alignment factor */
+ .byte 8 /* Return address register column */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+ .byte 0x0c /* DW_CFA_def_cfa */
+ .uleb128 4
+ .uleb128 4
+ .byte 0x88 /* DW_CFA_offset, column 0x8 */
+ .uleb128 1
+ .align 4
+.LENDCIE:
+
+ .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */
+.LSTARTFDE1:
+ .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */
+ .long .LSTART_vsyscall-. /* PC-relative start address */
+ .long .LEND_vsyscall-.LSTART_vsyscall
+ .uleb128 0 /* Augmentation length */
+ /* What follows are the instructions for the table generation.
+ We have to record all changes of the stack pointer. */
+ .byte 0x04 /* DW_CFA_advance_loc4 */
+ .long .Lpush_ecx-.LSTART_vsyscall
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x08 /* RA at offset 8 now */
+ .byte 0x04 /* DW_CFA_advance_loc4 */
+ .long .Lpush_edx-.Lpush_ecx
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x0c /* RA at offset 12 now */
+ .byte 0x04 /* DW_CFA_advance_loc4 */
+ .long .Lenter_kernel-.Lpush_edx
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x10 /* RA at offset 16 now */
+ .byte 0x85, 0x04 /* DW_CFA_offset %ebp -16 */
+ /* Finally the epilogue. */
+ .byte 0x04 /* DW_CFA_advance_loc4 */
+ .long .Lpop_ebp-.Lenter_kernel
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x12 /* RA at offset 12 now */
+ .byte 0xc5 /* DW_CFA_restore %ebp */
+ .byte 0x04 /* DW_CFA_advance_loc4 */
+ .long .Lpop_edx-.Lpop_ebp
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x08 /* RA at offset 8 now */
+ .byte 0x04 /* DW_CFA_advance_loc4 */
+ .long .Lpop_ecx-.Lpop_edx
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x04 /* RA at offset 4 now */
+ .align 4
+.LENDFDE1:
+
+#define SYSCALL_ENTER_KERNEL int $0x80
+#include "vsyscall-sigreturn.S"
diff --git a/trunk/arch/x86/ia32/vsyscall.lds b/trunk/arch/x86/ia32/vsyscall.lds
new file mode 100644
index 000000000000..1dc86ff5bcb9
--- /dev/null
+++ b/trunk/arch/x86/ia32/vsyscall.lds
@@ -0,0 +1,80 @@
+/*
+ * Linker script for vsyscall DSO. The vsyscall page is an ELF shared
+ * object prelinked to its virtual address. This script controls its layout.
+ */
+
+/* This must match . */
+VSYSCALL_BASE = 0xffffe000;
+
+SECTIONS
+{
+ . = VSYSCALL_BASE + SIZEOF_HEADERS;
+
+ .hash : { *(.hash) } :text
+ .gnu.hash : { *(.gnu.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .gnu.version : { *(.gnu.version) }
+ .gnu.version_d : { *(.gnu.version_d) }
+ .gnu.version_r : { *(.gnu.version_r) }
+
+ /* This linker script is used both with -r and with -shared.
+ For the layouts to match, we need to skip more than enough
+ space for the dynamic symbol table et al. If this amount
+ is insufficient, ld -shared will barf. Just increase it here. */
+ . = VSYSCALL_BASE + 0x400;
+
+ .text.vsyscall : { *(.text.vsyscall) } :text =0x90909090
+
+ /* This is an 32bit object and we cannot easily get the offsets
+ into the 64bit kernel. Just hardcode them here. This assumes
+ that all the stubs don't need more than 0x100 bytes. */
+ . = VSYSCALL_BASE + 0x500;
+
+ .text.sigreturn : { *(.text.sigreturn) } :text =0x90909090
+
+ . = VSYSCALL_BASE + 0x600;
+
+ .text.rtsigreturn : { *(.text.rtsigreturn) } :text =0x90909090
+
+ .note : { *(.note.*) } :text :note
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+ .dynamic : { *(.dynamic) } :text :dynamic
+ .useless : {
+ *(.got.plt) *(.got)
+ *(.data .data.* .gnu.linkonce.d.*)
+ *(.dynbss)
+ *(.bss .bss.* .gnu.linkonce.b.*)
+ } :text
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+ text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+ eh_frame_hdr 0x6474e550; /* PT_GNU_EH_FRAME, but ld doesn't match the name */
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+ LINUX_2.5 {
+ global:
+ __kernel_vsyscall;
+ __kernel_sigreturn;
+ __kernel_rt_sigreturn;
+
+ local: *;
+ };
+}
+
+/* The ELF entry point can be used to set the AT_SYSINFO value. */
+ENTRY(__kernel_vsyscall);
diff --git a/trunk/arch/x86/kernel/Makefile b/trunk/arch/x86/kernel/Makefile
index 6f813009d44b..38573340b143 100644
--- a/trunk/arch/x86/kernel/Makefile
+++ b/trunk/arch/x86/kernel/Makefile
@@ -1,91 +1,9 @@
-#
-# Makefile for the linux kernel.
-#
-
-extra-y := head_$(BITS).o init_task.o vmlinux.lds
-extra-$(CONFIG_X86_64) += head64.o
-
-CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
-CFLAGS_vsyscall_64.o := $(PROFILING) -g0
-
-obj-y := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
-obj-y += traps_$(BITS).o irq_$(BITS).o
-obj-y += time_$(BITS).o ioport.o ldt.o
-obj-y += setup_$(BITS).o i8259_$(BITS).o
-obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
-obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
-obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o setup64.o
-obj-y += pci-dma_$(BITS).o bootflag.o e820_$(BITS).o
-obj-y += quirks.o i8237.o topology.o kdebugfs.o
-obj-y += alternative.o i8253.o
-obj-$(CONFIG_X86_64) += pci-nommu_64.o bugs_64.o
-obj-y += tsc_$(BITS).o io_delay.o rtc.o
-
-obj-y += i387.o
-obj-y += ptrace.o
-obj-y += ds.o
-obj-$(CONFIG_X86_32) += tls.o
-obj-$(CONFIG_IA32_EMULATION) += tls.o
-obj-y += step.o
-obj-$(CONFIG_STACKTRACE) += stacktrace.o
-obj-y += cpu/
-obj-y += acpi/
-obj-$(CONFIG_X86_BIOS_REBOOT) += reboot.o
-obj-$(CONFIG_X86_64) += reboot.o
-obj-$(CONFIG_MCA) += mca_32.o
-obj-$(CONFIG_X86_MSR) += msr.o
-obj-$(CONFIG_X86_CPUID) += cpuid.o
-obj-$(CONFIG_MICROCODE) += microcode.o
-obj-$(CONFIG_PCI) += early-quirks.o
-obj-$(CONFIG_APM) += apm_32.o
-obj-$(CONFIG_X86_SMP) += smp_$(BITS).o smpboot_$(BITS).o tsc_sync.o
-obj-$(CONFIG_X86_32_SMP) += smpcommon_32.o
-obj-$(CONFIG_X86_64_SMP) += smp_64.o smpboot_64.o tsc_sync.o
-obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o
-obj-$(CONFIG_X86_MPPARSE) += mpparse_$(BITS).o
-obj-$(CONFIG_X86_LOCAL_APIC) += apic_$(BITS).o nmi_$(BITS).o
-obj-$(CONFIG_X86_IO_APIC) += io_apic_$(BITS).o
-obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o
-obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o
-obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o
-obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
-obj-$(CONFIG_X86_NUMAQ) += numaq_32.o
-obj-$(CONFIG_X86_SUMMIT_NUMA) += summit_32.o
-obj-$(CONFIG_X86_VSMP) += vsmp_64.o
-obj-$(CONFIG_KPROBES) += kprobes.o
-obj-$(CONFIG_MODULES) += module_$(BITS).o
-obj-$(CONFIG_ACPI_SRAT) += srat_32.o
-obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o
-obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o
-obj-$(CONFIG_VM86) += vm86_32.o
-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-
-obj-$(CONFIG_HPET_TIMER) += hpet.o
-
-obj-$(CONFIG_K8_NB) += k8.o
-obj-$(CONFIG_MGEODE_LX) += geode_32.o mfgpt_32.o
-obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
-obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o
-
-obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o
-obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o
-
-ifdef CONFIG_INPUT_PCSPKR
-obj-y += pcspeaker.o
+ifeq ($(CONFIG_X86_32),y)
+include ${srctree}/arch/x86/kernel/Makefile_32
+else
+include ${srctree}/arch/x86/kernel/Makefile_64
endif
-obj-$(CONFIG_SCx200) += scx200_32.o
-
-###
-# 64 bit specific files
-ifeq ($(CONFIG_X86_64),y)
- obj-y += genapic_64.o genapic_flat_64.o
- obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o
- obj-$(CONFIG_AUDIT) += audit_64.o
- obj-$(CONFIG_PM) += suspend_64.o
- obj-$(CONFIG_HIBERNATION) += suspend_asm_64.o
-
- obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o
- obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o
- obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o
-endif
+# Workaround to delete .lds files with make clean
+# The problem is that we do not enter Makefile_32 with make clean.
+clean-files := vsyscall*.lds vsyscall*.so
diff --git a/trunk/arch/x86/kernel/Makefile_32 b/trunk/arch/x86/kernel/Makefile_32
new file mode 100644
index 000000000000..a7bc93c27662
--- /dev/null
+++ b/trunk/arch/x86/kernel/Makefile_32
@@ -0,0 +1,88 @@
+#
+# Makefile for the linux kernel.
+#
+
+extra-y := head_32.o init_task.o vmlinux.lds
+CPPFLAGS_vmlinux.lds += -Ui386
+
+obj-y := process_32.o signal_32.o entry_32.o traps_32.o irq_32.o \
+ ptrace_32.o time_32.o ioport_32.o ldt_32.o setup_32.o i8259_32.o sys_i386_32.o \
+ pci-dma_32.o i386_ksyms_32.o i387_32.o bootflag.o e820_32.o\
+ quirks.o i8237.o topology.o alternative.o i8253.o tsc_32.o
+
+obj-$(CONFIG_STACKTRACE) += stacktrace.o
+obj-y += cpu/
+obj-y += acpi/
+obj-$(CONFIG_X86_BIOS_REBOOT) += reboot_32.o
+obj-$(CONFIG_MCA) += mca_32.o
+obj-$(CONFIG_X86_MSR) += msr.o
+obj-$(CONFIG_X86_CPUID) += cpuid.o
+obj-$(CONFIG_MICROCODE) += microcode.o
+obj-$(CONFIG_PCI) += early-quirks.o
+obj-$(CONFIG_APM) += apm_32.o
+obj-$(CONFIG_X86_SMP) += smp_32.o smpboot_32.o tsc_sync.o
+obj-$(CONFIG_SMP) += smpcommon_32.o
+obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_32.o
+obj-$(CONFIG_X86_MPPARSE) += mpparse_32.o
+obj-$(CONFIG_X86_LOCAL_APIC) += apic_32.o nmi_32.o
+obj-$(CONFIG_X86_IO_APIC) += io_apic_32.o
+obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o
+obj-$(CONFIG_KEXEC) += machine_kexec_32.o relocate_kernel_32.o crash.o
+obj-$(CONFIG_CRASH_DUMP) += crash_dump_32.o
+obj-$(CONFIG_X86_NUMAQ) += numaq_32.o
+obj-$(CONFIG_X86_SUMMIT_NUMA) += summit_32.o
+obj-$(CONFIG_KPROBES) += kprobes_32.o
+obj-$(CONFIG_MODULES) += module_32.o
+obj-y += sysenter_32.o vsyscall_32.o
+obj-$(CONFIG_ACPI_SRAT) += srat_32.o
+obj-$(CONFIG_EFI) += efi_32.o efi_stub_32.o
+obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o
+obj-$(CONFIG_VM86) += vm86_32.o
+obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+obj-$(CONFIG_HPET_TIMER) += hpet.o
+obj-$(CONFIG_K8_NB) += k8.o
+obj-$(CONFIG_MGEODE_LX) += geode_32.o mfgpt_32.o
+
+obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o
+obj-$(CONFIG_PARAVIRT) += paravirt_32.o
+obj-y += pcspeaker.o
+
+obj-$(CONFIG_SCx200) += scx200_32.o
+
+# vsyscall_32.o contains the vsyscall DSO images as __initdata.
+# We must build both images before we can assemble it.
+# Note: kbuild does not track this dependency due to usage of .incbin
+$(obj)/vsyscall_32.o: $(obj)/vsyscall-int80_32.so $(obj)/vsyscall-sysenter_32.so
+targets += $(foreach F,int80 sysenter,vsyscall-$F_32.o vsyscall-$F_32.so)
+targets += vsyscall-note_32.o vsyscall_32.lds
+
+# The DSO images are built using a special linker script.
+quiet_cmd_syscall = SYSCALL $@
+ cmd_syscall = $(CC) -m elf_i386 -nostdlib $(SYSCFLAGS_$(@F)) \
+ -Wl,-T,$(filter-out FORCE,$^) -o $@
+
+export CPPFLAGS_vsyscall_32.lds += -P -C -Ui386
+
+vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 \
+ $(call ld-option, -Wl$(comma)--hash-style=sysv)
+SYSCFLAGS_vsyscall-sysenter_32.so = $(vsyscall-flags)
+SYSCFLAGS_vsyscall-int80_32.so = $(vsyscall-flags)
+
+$(obj)/vsyscall-int80_32.so $(obj)/vsyscall-sysenter_32.so: \
+$(obj)/vsyscall-%.so: $(src)/vsyscall_32.lds \
+ $(obj)/vsyscall-%.o $(obj)/vsyscall-note_32.o FORCE
+ $(call if_changed,syscall)
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO. With ld -R we can then refer to
+# these symbols in the kernel code rather than hand-coded addresses.
+extra-y += vsyscall-syms.o
+$(obj)/built-in.o: $(obj)/vsyscall-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/vsyscall-syms.o
+
+SYSCFLAGS_vsyscall-syms.o = -r
+$(obj)/vsyscall-syms.o: $(src)/vsyscall_32.lds \
+ $(obj)/vsyscall-sysenter_32.o $(obj)/vsyscall-note_32.o FORCE
+ $(call if_changed,syscall)
+
+
diff --git a/trunk/arch/x86/kernel/Makefile_64 b/trunk/arch/x86/kernel/Makefile_64
new file mode 100644
index 000000000000..5a88890d8ee9
--- /dev/null
+++ b/trunk/arch/x86/kernel/Makefile_64
@@ -0,0 +1,45 @@
+#
+# Makefile for the linux kernel.
+#
+
+extra-y := head_64.o head64.o init_task.o vmlinux.lds
+CPPFLAGS_vmlinux.lds += -Ux86_64
+EXTRA_AFLAGS := -traditional
+
+obj-y := process_64.o signal_64.o entry_64.o traps_64.o irq_64.o \
+ ptrace_64.o time_64.o ioport_64.o ldt_64.o setup_64.o i8259_64.o sys_x86_64.o \
+ x8664_ksyms_64.o i387_64.o syscall_64.o vsyscall_64.o \
+ setup64.o bootflag.o e820_64.o reboot_64.o quirks.o i8237.o \
+ pci-dma_64.o pci-nommu_64.o alternative.o hpet.o tsc_64.o bugs_64.o \
+ i8253.o
+
+obj-$(CONFIG_STACKTRACE) += stacktrace.o
+obj-y += cpu/
+obj-y += acpi/
+obj-$(CONFIG_X86_MSR) += msr.o
+obj-$(CONFIG_MICROCODE) += microcode.o
+obj-$(CONFIG_X86_CPUID) += cpuid.o
+obj-$(CONFIG_SMP) += smp_64.o smpboot_64.o trampoline_64.o tsc_sync.o
+obj-y += apic_64.o nmi_64.o
+obj-y += io_apic_64.o mpparse_64.o genapic_64.o genapic_flat_64.o
+obj-$(CONFIG_KEXEC) += machine_kexec_64.o relocate_kernel_64.o crash.o
+obj-$(CONFIG_CRASH_DUMP) += crash_dump_64.o
+obj-$(CONFIG_PM) += suspend_64.o
+obj-$(CONFIG_HIBERNATION) += suspend_asm_64.o
+obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o
+obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o
+obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o
+obj-$(CONFIG_KPROBES) += kprobes_64.o
+obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o
+obj-$(CONFIG_X86_VSMP) += vsmp_64.o
+obj-$(CONFIG_K8_NB) += k8.o
+obj-$(CONFIG_AUDIT) += audit_64.o
+
+obj-$(CONFIG_MODULES) += module_64.o
+obj-$(CONFIG_PCI) += early-quirks.o
+
+obj-y += topology.o
+obj-y += pcspeaker.o
+
+CFLAGS_vsyscall_64.o := $(PROFILING) -g0
diff --git a/trunk/arch/x86/kernel/acpi/Makefile b/trunk/arch/x86/kernel/acpi/Makefile
index 19d3d6e9d09b..1351c3982ee4 100644
--- a/trunk/arch/x86/kernel/acpi/Makefile
+++ b/trunk/arch/x86/kernel/acpi/Makefile
@@ -1,5 +1,5 @@
obj-$(CONFIG_ACPI) += boot.o
-obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o
+obj-$(CONFIG_ACPI_SLEEP) += sleep_$(BITS).o wakeup_$(BITS).o
ifneq ($(CONFIG_ACPI_PROCESSOR),)
obj-y += cstate.o processor.o
diff --git a/trunk/arch/x86/kernel/acpi/sleep.c b/trunk/arch/x86/kernel/acpi/sleep.c
deleted file mode 100644
index 6bc815cd8cb3..000000000000
--- a/trunk/arch/x86/kernel/acpi/sleep.c
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * sleep.c - x86-specific ACPI sleep support.
- *
- * Copyright (C) 2001-2003 Patrick Mochel
- * Copyright (C) 2001-2003 Pavel Machek
- */
-
-#include
-#include
-#include
-#include
-
-#include
-
-/* address in low memory of the wakeup routine. */
-unsigned long acpi_wakeup_address = 0;
-unsigned long acpi_realmode_flags;
-extern char wakeup_start, wakeup_end;
-
-extern unsigned long acpi_copy_wakeup_routine(unsigned long);
-
-/**
- * acpi_save_state_mem - save kernel state
- *
- * Create an identity mapped page table and copy the wakeup routine to
- * low memory.
- */
-int acpi_save_state_mem(void)
-{
- if (!acpi_wakeup_address) {
- printk(KERN_ERR "Could not allocate memory during boot, S3 disabled\n");
- return -ENOMEM;
- }
- memcpy((void *)acpi_wakeup_address, &wakeup_start,
- &wakeup_end - &wakeup_start);
- acpi_copy_wakeup_routine(acpi_wakeup_address);
-
- return 0;
-}
-
-/*
- * acpi_restore_state - undo effects of acpi_save_state_mem
- */
-void acpi_restore_state_mem(void)
-{
-}
-
-
-/**
- * acpi_reserve_bootmem - do _very_ early ACPI initialisation
- *
- * We allocate a page from the first 1MB of memory for the wakeup
- * routine for when we come back from a sleep state. The
- * runtime allocator allows specification of <16MB pages, but not
- * <1MB pages.
- */
-void __init acpi_reserve_bootmem(void)
-{
- if ((&wakeup_end - &wakeup_start) > PAGE_SIZE*2) {
- printk(KERN_ERR
- "ACPI: Wakeup code way too big, S3 disabled.\n");
- return;
- }
-
- acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE*2);
- if (!acpi_wakeup_address)
- printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
-}
-
-
-static int __init acpi_sleep_setup(char *str)
-{
- while ((str != NULL) && (*str != '\0')) {
- if (strncmp(str, "s3_bios", 7) == 0)
- acpi_realmode_flags |= 1;
- if (strncmp(str, "s3_mode", 7) == 0)
- acpi_realmode_flags |= 2;
- if (strncmp(str, "s3_beep", 7) == 0)
- acpi_realmode_flags |= 4;
- str = strchr(str, ',');
- if (str != NULL)
- str += strspn(str, ", \t");
- }
- return 1;
-}
-
-__setup("acpi_sleep=", acpi_sleep_setup);
diff --git a/trunk/arch/x86/kernel/acpi/sleep_32.c b/trunk/arch/x86/kernel/acpi/sleep_32.c
index 63fe5525e026..10699489cfe7 100644
--- a/trunk/arch/x86/kernel/acpi/sleep_32.c
+++ b/trunk/arch/x86/kernel/acpi/sleep_32.c
@@ -12,6 +12,76 @@
#include
+/* address in low memory of the wakeup routine. */
+unsigned long acpi_wakeup_address = 0;
+unsigned long acpi_realmode_flags;
+extern char wakeup_start, wakeup_end;
+
+extern unsigned long FASTCALL(acpi_copy_wakeup_routine(unsigned long));
+
+/**
+ * acpi_save_state_mem - save kernel state
+ *
+ * Create an identity mapped page table and copy the wakeup routine to
+ * low memory.
+ */
+int acpi_save_state_mem(void)
+{
+ if (!acpi_wakeup_address)
+ return 1;
+ memcpy((void *)acpi_wakeup_address, &wakeup_start,
+ &wakeup_end - &wakeup_start);
+ acpi_copy_wakeup_routine(acpi_wakeup_address);
+
+ return 0;
+}
+
+/*
+ * acpi_restore_state - undo effects of acpi_save_state_mem
+ */
+void acpi_restore_state_mem(void)
+{
+}
+
+/**
+ * acpi_reserve_bootmem - do _very_ early ACPI initialisation
+ *
+ * We allocate a page from the first 1MB of memory for the wakeup
+ * routine for when we come back from a sleep state. The
+ * runtime allocator allows specification of <16MB pages, but not
+ * <1MB pages.
+ */
+void __init acpi_reserve_bootmem(void)
+{
+ if ((&wakeup_end - &wakeup_start) > PAGE_SIZE) {
+ printk(KERN_ERR
+ "ACPI: Wakeup code way too big, S3 disabled.\n");
+ return;
+ }
+
+ acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE);
+ if (!acpi_wakeup_address)
+ printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
+}
+
+static int __init acpi_sleep_setup(char *str)
+{
+ while ((str != NULL) && (*str != '\0')) {
+ if (strncmp(str, "s3_bios", 7) == 0)
+ acpi_realmode_flags |= 1;
+ if (strncmp(str, "s3_mode", 7) == 0)
+ acpi_realmode_flags |= 2;
+ if (strncmp(str, "s3_beep", 7) == 0)
+ acpi_realmode_flags |= 4;
+ str = strchr(str, ',');
+ if (str != NULL)
+ str += strspn(str, ", \t");
+ }
+ return 1;
+}
+
+__setup("acpi_sleep=", acpi_sleep_setup);
+
/* Ouch, we want to delete this. We already have better version in userspace, in
s2ram from suspend.sf.net project */
static __init int reset_videomode_after_s3(const struct dmi_system_id *d)
diff --git a/trunk/arch/x86/kernel/acpi/sleep_64.c b/trunk/arch/x86/kernel/acpi/sleep_64.c
new file mode 100644
index 000000000000..da42de261ba8
--- /dev/null
+++ b/trunk/arch/x86/kernel/acpi/sleep_64.c
@@ -0,0 +1,117 @@
+/*
+ * acpi.c - Architecture-Specific Low-Level ACPI Support
+ *
+ * Copyright (C) 2001, 2002 Paul Diefenbaugh
+ * Copyright (C) 2001 Jun Nakajima
+ * Copyright (C) 2001 Patrick Mochel
+ * Copyright (C) 2002 Andi Kleen, SuSE Labs (x86-64 port)
+ * Copyright (C) 2003 Pavel Machek, SuSE Labs
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+/* --------------------------------------------------------------------------
+ Low-Level Sleep Support
+ -------------------------------------------------------------------------- */
+
+/* address in low memory of the wakeup routine. */
+unsigned long acpi_wakeup_address = 0;
+unsigned long acpi_realmode_flags;
+extern char wakeup_start, wakeup_end;
+
+extern unsigned long acpi_copy_wakeup_routine(unsigned long);
+
+/**
+ * acpi_save_state_mem - save kernel state
+ *
+ * Create an identity mapped page table and copy the wakeup routine to
+ * low memory.
+ */
+int acpi_save_state_mem(void)
+{
+ memcpy((void *)acpi_wakeup_address, &wakeup_start,
+ &wakeup_end - &wakeup_start);
+ acpi_copy_wakeup_routine(acpi_wakeup_address);
+
+ return 0;
+}
+
+/*
+ * acpi_restore_state
+ */
+void acpi_restore_state_mem(void)
+{
+}
+
+/**
+ * acpi_reserve_bootmem - do _very_ early ACPI initialisation
+ *
+ * We allocate a page in low memory for the wakeup
+ * routine for when we come back from a sleep state. The
+ * runtime allocator allows specification of <16M pages, but not
+ * <1M pages.
+ */
+void __init acpi_reserve_bootmem(void)
+{
+ acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE*2);
+ if ((&wakeup_end - &wakeup_start) > (PAGE_SIZE*2))
+ printk(KERN_CRIT
+ "ACPI: Wakeup code way too big, will crash on attempt"
+ " to suspend\n");
+}
+
+static int __init acpi_sleep_setup(char *str)
+{
+ while ((str != NULL) && (*str != '\0')) {
+ if (strncmp(str, "s3_bios", 7) == 0)
+ acpi_realmode_flags |= 1;
+ if (strncmp(str, "s3_mode", 7) == 0)
+ acpi_realmode_flags |= 2;
+ if (strncmp(str, "s3_beep", 7) == 0)
+ acpi_realmode_flags |= 4;
+ str = strchr(str, ',');
+ if (str != NULL)
+ str += strspn(str, ", \t");
+ }
+ return 1;
+}
+
+__setup("acpi_sleep=", acpi_sleep_setup);
+
diff --git a/trunk/arch/x86/kernel/acpi/wakeup_32.S b/trunk/arch/x86/kernel/acpi/wakeup_32.S
index f53e3277f8e5..1e931aaf2ef6 100644
--- a/trunk/arch/x86/kernel/acpi/wakeup_32.S
+++ b/trunk/arch/x86/kernel/acpi/wakeup_32.S
@@ -1,4 +1,4 @@
- .section .text.page_aligned
+.text
#include
#include
#include
diff --git a/trunk/arch/x86/kernel/acpi/wakeup_64.S b/trunk/arch/x86/kernel/acpi/wakeup_64.S
index 2e1b9e0d0767..5ed3bc5c61d7 100644
--- a/trunk/arch/x86/kernel/acpi/wakeup_64.S
+++ b/trunk/arch/x86/kernel/acpi/wakeup_64.S
@@ -344,13 +344,13 @@ do_suspend_lowlevel:
call save_processor_state
movq $saved_context, %rax
- movq %rsp, pt_regs_sp(%rax)
- movq %rbp, pt_regs_bp(%rax)
- movq %rsi, pt_regs_si(%rax)
- movq %rdi, pt_regs_di(%rax)
- movq %rbx, pt_regs_bx(%rax)
- movq %rcx, pt_regs_cx(%rax)
- movq %rdx, pt_regs_dx(%rax)
+ movq %rsp, pt_regs_rsp(%rax)
+ movq %rbp, pt_regs_rbp(%rax)
+ movq %rsi, pt_regs_rsi(%rax)
+ movq %rdi, pt_regs_rdi(%rax)
+ movq %rbx, pt_regs_rbx(%rax)
+ movq %rcx, pt_regs_rcx(%rax)
+ movq %rdx, pt_regs_rdx(%rax)
movq %r8, pt_regs_r8(%rax)
movq %r9, pt_regs_r9(%rax)
movq %r10, pt_regs_r10(%rax)
@@ -360,7 +360,7 @@ do_suspend_lowlevel:
movq %r14, pt_regs_r14(%rax)
movq %r15, pt_regs_r15(%rax)
pushfq
- popq pt_regs_flags(%rax)
+ popq pt_regs_eflags(%rax)
movq $.L97, saved_rip(%rip)
@@ -391,15 +391,15 @@ do_suspend_lowlevel:
movq %rbx, %cr2
movq saved_context_cr0(%rax), %rbx
movq %rbx, %cr0
- pushq pt_regs_flags(%rax)
+ pushq pt_regs_eflags(%rax)
popfq
- movq pt_regs_sp(%rax), %rsp
- movq pt_regs_bp(%rax), %rbp
- movq pt_regs_si(%rax), %rsi
- movq pt_regs_di(%rax), %rdi
- movq pt_regs_bx(%rax), %rbx
- movq pt_regs_cx(%rax), %rcx
- movq pt_regs_dx(%rax), %rdx
+ movq pt_regs_rsp(%rax), %rsp
+ movq pt_regs_rbp(%rax), %rbp
+ movq pt_regs_rsi(%rax), %rsi
+ movq pt_regs_rdi(%rax), %rdi
+ movq pt_regs_rbx(%rax), %rbx
+ movq pt_regs_rcx(%rax), %rcx
+ movq pt_regs_rdx(%rax), %rdx
movq pt_regs_r8(%rax), %r8
movq pt_regs_r9(%rax), %r9
movq pt_regs_r10(%rax), %r10
diff --git a/trunk/arch/x86/kernel/alternative.c b/trunk/arch/x86/kernel/alternative.c
index 45d79ea890ae..d6405e0842b5 100644
--- a/trunk/arch/x86/kernel/alternative.c
+++ b/trunk/arch/x86/kernel/alternative.c
@@ -273,7 +273,6 @@ struct smp_alt_module {
};
static LIST_HEAD(smp_alt_modules);
static DEFINE_SPINLOCK(smp_alt);
-static int smp_mode = 1; /* protected by smp_alt */
void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
@@ -342,13 +341,12 @@ void alternatives_smp_switch(int smp)
#ifdef CONFIG_LOCKDEP
/*
- * Older binutils section handling bug prevented
- * alternatives-replacement from working reliably.
- *
- * If this still occurs then you should see a hang
- * or crash shortly after this line:
+ * A not yet fixed binutils section handling bug prevents
+ * alternatives-replacement from working reliably, so turn
+ * it off:
*/
- printk("lockdep: fixing up alternatives.\n");
+ printk("lockdep: not fixing up alternatives.\n");
+ return;
#endif
if (noreplace_smp || smp_alt_once)
@@ -356,29 +354,21 @@ void alternatives_smp_switch(int smp)
BUG_ON(!smp && (num_online_cpus() > 1));
spin_lock_irqsave(&smp_alt, flags);
-
- /*
- * Avoid unnecessary switches because it forces JIT based VMs to
- * throw away all cached translations, which can be quite costly.
- */
- if (smp == smp_mode) {
- /* nothing */
- } else if (smp) {
+ if (smp) {
printk(KERN_INFO "SMP alternatives: switching to SMP code\n");
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
+ clear_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
+ clear_bit(X86_FEATURE_UP, cpu_data(0).x86_capability);
list_for_each_entry(mod, &smp_alt_modules, next)
alternatives_smp_lock(mod->locks, mod->locks_end,
mod->text, mod->text_end);
} else {
printk(KERN_INFO "SMP alternatives: switching to UP code\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
+ set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
+ set_bit(X86_FEATURE_UP, cpu_data(0).x86_capability);
list_for_each_entry(mod, &smp_alt_modules, next)
alternatives_smp_unlock(mod->locks, mod->locks_end,
mod->text, mod->text_end);
}
- smp_mode = smp;
spin_unlock_irqrestore(&smp_alt, flags);
}
@@ -441,9 +431,8 @@ void __init alternative_instructions(void)
if (smp_alt_once) {
if (1 == num_possible_cpus()) {
printk(KERN_INFO "SMP alternatives: switching to UP code\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
-
+ set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
+ set_bit(X86_FEATURE_UP, cpu_data(0).x86_capability);
alternatives_smp_unlock(__smp_locks, __smp_locks_end,
_text, _etext);
}
@@ -451,10 +440,7 @@ void __init alternative_instructions(void)
alternatives_smp_module_add(NULL, "core kernel",
__smp_locks, __smp_locks_end,
_text, _etext);
-
- /* Only switch to UP mode if we don't immediately boot others */
- if (num_possible_cpus() == 1 || setup_max_cpus <= 1)
- alternatives_smp_switch(0);
+ alternatives_smp_switch(0);
}
#endif
apply_paravirt(__parainstructions, __parainstructions_end);
diff --git a/trunk/arch/x86/kernel/aperture_64.c b/trunk/arch/x86/kernel/aperture_64.c
index 608152a2a05e..5b6992799c9d 100644
--- a/trunk/arch/x86/kernel/aperture_64.c
+++ b/trunk/arch/x86/kernel/aperture_64.c
@@ -1,12 +1,12 @@
-/*
+/*
* Firmware replacement code.
- *
+ *
* Work around broken BIOSes that don't set an aperture or only set the
- * aperture in the AGP bridge.
- * If all fails map the aperture over some low memory. This is cheaper than
- * doing bounce buffering. The memory is lost. This is done at early boot
- * because only the bootmem allocator can allocate 32+MB.
- *
+ * aperture in the AGP bridge.
+ * If all fails map the aperture over some low memory. This is cheaper than
+ * doing bounce buffering. The memory is lost. This is done at early boot
+ * because only the bootmem allocator can allocate 32+MB.
+ *
* Copyright 2002 Andi Kleen, SuSE Labs.
*/
#include
@@ -30,7 +30,7 @@ int gart_iommu_aperture_disabled __initdata = 0;
int gart_iommu_aperture_allowed __initdata = 0;
int fallback_aper_order __initdata = 1; /* 64MB */
-int fallback_aper_force __initdata = 0;
+int fallback_aper_force __initdata = 0;
int fix_aperture __initdata = 1;
@@ -49,270 +49,167 @@ static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
/* This code runs before the PCI subsystem is initialized, so just
access the northbridge directly. */
-static u32 __init allocate_aperture(void)
+static u32 __init allocate_aperture(void)
{
u32 aper_size;
- void *p;
+ void *p;
- if (fallback_aper_order > 7)
- fallback_aper_order = 7;
- aper_size = (32 * 1024 * 1024) << fallback_aper_order;
+ if (fallback_aper_order > 7)
+ fallback_aper_order = 7;
+ aper_size = (32 * 1024 * 1024) << fallback_aper_order;
- /*
- * Aperture has to be naturally aligned. This means a 2GB aperture
- * won't have much chance of finding a place in the lower 4GB of
- * memory. Unfortunately we cannot move it up because that would
- * make the IOMMU useless.
+ /*
+ * Aperture has to be naturally aligned. This means an 2GB aperture won't
+ * have much chance of finding a place in the lower 4GB of memory.
+ * Unfortunately we cannot move it up because that would make the
+ * IOMMU useless.
*/
p = __alloc_bootmem_nopanic(aper_size, aper_size, 0);
if (!p || __pa(p)+aper_size > 0xffffffff) {
- printk(KERN_ERR
- "Cannot allocate aperture memory hole (%p,%uK)\n",
- p, aper_size>>10);
+ printk("Cannot allocate aperture memory hole (%p,%uK)\n",
+ p, aper_size>>10);
if (p)
free_bootmem(__pa(p), aper_size);
return 0;
}
- printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
- aper_size >> 10, __pa(p));
+ printk("Mapping aperture over %d KB of RAM @ %lx\n",
+ aper_size >> 10, __pa(p));
insert_aperture_resource((u32)__pa(p), aper_size);
-
- return (u32)__pa(p);
+ return (u32)__pa(p);
}
static int __init aperture_valid(u64 aper_base, u32 aper_size)
-{
- if (!aper_base)
+{
+ if (!aper_base)
return 0;
-
- if (aper_base + aper_size > 0x100000000UL) {
- printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n");
+ if (aper_size < 64*1024*1024) {
+ printk("Aperture too small (%d MB)\n", aper_size>>20);
return 0;
}
- if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
- printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
- return 0;
- }
- if (aper_size < 64*1024*1024) {
- printk(KERN_ERR "Aperture too small (%d MB)\n", aper_size>>20);
- return 0;
+ if (aper_base + aper_size > 0x100000000UL) {
+ printk("Aperture beyond 4GB. Ignoring.\n");
+ return 0;
}
-
+ if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+ printk("Aperture pointing to e820 RAM. Ignoring.\n");
+ return 0;
+ }
return 1;
-}
+}
/* Find a PCI capability */
-static __u32 __init find_cap(int num, int slot, int func, int cap)
-{
- int bytes;
+static __u32 __init find_cap(int num, int slot, int func, int cap)
+{
u8 pos;
-
- if (!(read_pci_config_16(num, slot, func, PCI_STATUS) &
- PCI_STATUS_CAP_LIST))
+ int bytes;
+ if (!(read_pci_config_16(num,slot,func,PCI_STATUS) & PCI_STATUS_CAP_LIST))
return 0;
-
- pos = read_pci_config_byte(num, slot, func, PCI_CAPABILITY_LIST);
- for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) {
+ pos = read_pci_config_byte(num,slot,func,PCI_CAPABILITY_LIST);
+ for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) {
u8 id;
-
- pos &= ~3;
- id = read_pci_config_byte(num, slot, func, pos+PCI_CAP_LIST_ID);
+ pos &= ~3;
+ id = read_pci_config_byte(num,slot,func,pos+PCI_CAP_LIST_ID);
if (id == 0xff)
break;
- if (id == cap)
- return pos;
- pos = read_pci_config_byte(num, slot, func,
- pos+PCI_CAP_LIST_NEXT);
- }
+ if (id == cap)
+ return pos;
+ pos = read_pci_config_byte(num,slot,func,pos+PCI_CAP_LIST_NEXT);
+ }
return 0;
-}
+}
/* Read a standard AGPv3 bridge header */
static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
-{
+{
u32 apsize;
u32 apsizereg;
int nbits;
u32 aper_low, aper_hi;
u64 aper;
- printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", num, slot, func);
- apsizereg = read_pci_config_16(num, slot, func, cap + 0x14);
+ printk("AGP bridge at %02x:%02x:%02x\n", num, slot, func);
+ apsizereg = read_pci_config_16(num,slot,func, cap + 0x14);
if (apsizereg == 0xffffffff) {
- printk(KERN_ERR "APSIZE in AGP bridge unreadable\n");
+ printk("APSIZE in AGP bridge unreadable\n");
return 0;
}
apsize = apsizereg & 0xfff;
/* Some BIOS use weird encodings not in the AGPv3 table. */
- if (apsize & 0xff)
- apsize |= 0xf00;
+ if (apsize & 0xff)
+ apsize |= 0xf00;
nbits = hweight16(apsize);
*order = 7 - nbits;
if ((int)*order < 0) /* < 32MB */
*order = 0;
-
- aper_low = read_pci_config(num, slot, func, 0x10);
- aper_hi = read_pci_config(num, slot, func, 0x14);
+
+ aper_low = read_pci_config(num,slot,func, 0x10);
+ aper_hi = read_pci_config(num,slot,func,0x14);
aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32);
- printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n",
- aper, 32 << *order, apsizereg);
+ printk("Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n",
+ aper, 32 << *order, apsizereg);
if (!aperture_valid(aper, (32*1024*1024) << *order))
- return 0;
- return (u32)aper;
-}
+ return 0;
+ return (u32)aper;
+}
-/*
- * Look for an AGP bridge. Windows only expects the aperture in the
- * AGP bridge and some BIOS forget to initialize the Northbridge too.
- * Work around this here.
- *
- * Do an PCI bus scan by hand because we're running before the PCI
- * subsystem.
- *
- * All K8 AGP bridges are AGPv3 compliant, so we can do this scan
- * generically. It's probably overkill to always scan all slots because
- * the AGP bridges should be always an own bus on the HT hierarchy,
- * but do it here for future safety.
- */
+/* Look for an AGP bridge. Windows only expects the aperture in the
+ AGP bridge and some BIOS forget to initialize the Northbridge too.
+ Work around this here.
+
+ Do an PCI bus scan by hand because we're running before the PCI
+ subsystem.
+
+ All K8 AGP bridges are AGPv3 compliant, so we can do this scan
+ generically. It's probably overkill to always scan all slots because
+ the AGP bridges should be always an own bus on the HT hierarchy,
+ but do it here for future safety. */
static __u32 __init search_agp_bridge(u32 *order, int *valid_agp)
{
int num, slot, func;
/* Poor man's PCI discovery */
- for (num = 0; num < 256; num++) {
- for (slot = 0; slot < 32; slot++) {
- for (func = 0; func < 8; func++) {
+ for (num = 0; num < 256; num++) {
+ for (slot = 0; slot < 32; slot++) {
+ for (func = 0; func < 8; func++) {
u32 class, cap;
u8 type;
- class = read_pci_config(num, slot, func,
+ class = read_pci_config(num,slot,func,
PCI_CLASS_REVISION);
if (class == 0xffffffff)
- break;
-
- switch (class >> 16) {
+ break;
+
+ switch (class >> 16) {
case PCI_CLASS_BRIDGE_HOST:
case PCI_CLASS_BRIDGE_OTHER: /* needed? */
/* AGP bridge? */
- cap = find_cap(num, slot, func,
- PCI_CAP_ID_AGP);
+ cap = find_cap(num,slot,func,PCI_CAP_ID_AGP);
if (!cap)
break;
- *valid_agp = 1;
- return read_agp(num, slot, func, cap,
- order);
- }
-
+ *valid_agp = 1;
+ return read_agp(num,slot,func,cap,order);
+ }
+
/* No multi-function device? */
- type = read_pci_config_byte(num, slot, func,
+ type = read_pci_config_byte(num,slot,func,
PCI_HEADER_TYPE);
if (!(type & 0x80))
break;
- }
- }
+ }
+ }
}
- printk(KERN_INFO "No AGP bridge found\n");
-
+ printk("No AGP bridge found\n");
return 0;
}
-static int gart_fix_e820 __initdata = 1;
-
-static int __init parse_gart_mem(char *p)
-{
- if (!p)
- return -EINVAL;
-
- if (!strncmp(p, "off", 3))
- gart_fix_e820 = 0;
- else if (!strncmp(p, "on", 2))
- gart_fix_e820 = 1;
-
- return 0;
-}
-early_param("gart_fix_e820", parse_gart_mem);
-
-void __init early_gart_iommu_check(void)
-{
- /*
- * in case it is enabled before, esp for kexec/kdump,
- * previous kernel already enable that. memset called
- * by allocate_aperture/__alloc_bootmem_nopanic cause restart.
- * or second kernel have different position for GART hole. and new
- * kernel could use hole as RAM that is still used by GART set by
- * first kernel
- * or BIOS forget to put that in reserved.
- * try to update e820 to make that region as reserved.
- */
- int fix, num;
- u32 ctl;
- u32 aper_size = 0, aper_order = 0, last_aper_order = 0;
- u64 aper_base = 0, last_aper_base = 0;
- int aper_enabled = 0, last_aper_enabled = 0;
-
- if (!early_pci_allowed())
- return;
-
- fix = 0;
- for (num = 24; num < 32; num++) {
- if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
- continue;
-
- ctl = read_pci_config(0, num, 3, 0x90);
- aper_enabled = ctl & 1;
- aper_order = (ctl >> 1) & 7;
- aper_size = (32 * 1024 * 1024) << aper_order;
- aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff;
- aper_base <<= 25;
-
- if ((last_aper_order && aper_order != last_aper_order) ||
- (last_aper_base && aper_base != last_aper_base) ||
- (last_aper_enabled && aper_enabled != last_aper_enabled)) {
- fix = 1;
- break;
- }
- last_aper_order = aper_order;
- last_aper_base = aper_base;
- last_aper_enabled = aper_enabled;
- }
-
- if (!fix && !aper_enabled)
- return;
-
- if (!aper_base || !aper_size || aper_base + aper_size > 0x100000000UL)
- fix = 1;
-
- if (gart_fix_e820 && !fix && aper_enabled) {
- if (e820_any_mapped(aper_base, aper_base + aper_size,
- E820_RAM)) {
- /* reserved it, so we can resuse it in second kernel */
- printk(KERN_INFO "update e820 for GART\n");
- add_memory_region(aper_base, aper_size, E820_RESERVED);
- update_e820();
- }
- return;
- }
-
- /* different nodes have different setting, disable them all at first*/
- for (num = 24; num < 32; num++) {
- if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
- continue;
-
- ctl = read_pci_config(0, num, 3, 0x90);
- ctl &= ~1;
- write_pci_config(0, num, 3, 0x90, ctl);
- }
-
-}
-
void __init gart_iommu_hole_init(void)
-{
+{
+ int fix, num;
u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
u64 aper_base, last_aper_base = 0;
- int fix, num, valid_agp = 0;
- int node;
+ int valid_agp = 0;
if (gart_iommu_aperture_disabled || !fix_aperture ||
!early_pci_allowed())
@@ -321,26 +218,24 @@ void __init gart_iommu_hole_init(void)
printk(KERN_INFO "Checking aperture...\n");
fix = 0;
- node = 0;
- for (num = 24; num < 32; num++) {
+ for (num = 24; num < 32; num++) {
if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
continue;
iommu_detected = 1;
gart_iommu_aperture = 1;
- aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7;
- aper_size = (32 * 1024 * 1024) << aper_order;
+ aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7;
+ aper_size = (32 * 1024 * 1024) << aper_order;
aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff;
- aper_base <<= 25;
-
- printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n",
- node, aper_base, aper_size >> 20);
- node++;
+ aper_base <<= 25;
+ printk("CPU %d: aperture @ %Lx size %u MB\n", num-24,
+ aper_base, aper_size>>20);
+
if (!aperture_valid(aper_base, aper_size)) {
- fix = 1;
- break;
+ fix = 1;
+ break;
}
if ((last_aper_order && aper_order != last_aper_order) ||
@@ -350,64 +245,55 @@ void __init gart_iommu_hole_init(void)
}
last_aper_order = aper_order;
last_aper_base = aper_base;
- }
+ }
if (!fix && !fallback_aper_force) {
if (last_aper_base) {
unsigned long n = (32 * 1024 * 1024) << last_aper_order;
-
insert_aperture_resource((u32)last_aper_base, n);
}
- return;
+ return;
}
if (!fallback_aper_force)
- aper_alloc = search_agp_bridge(&aper_order, &valid_agp);
-
- if (aper_alloc) {
+ aper_alloc = search_agp_bridge(&aper_order, &valid_agp);
+
+ if (aper_alloc) {
/* Got the aperture from the AGP bridge */
} else if (swiotlb && !valid_agp) {
/* Do nothing */
} else if ((!no_iommu && end_pfn > MAX_DMA32_PFN) ||
force_iommu ||
valid_agp ||
- fallback_aper_force) {
- printk(KERN_ERR
- "Your BIOS doesn't leave a aperture memory hole\n");
- printk(KERN_ERR
- "Please enable the IOMMU option in the BIOS setup\n");
- printk(KERN_ERR
- "This costs you %d MB of RAM\n",
- 32 << fallback_aper_order);
+ fallback_aper_force) {
+ printk("Your BIOS doesn't leave a aperture memory hole\n");
+ printk("Please enable the IOMMU option in the BIOS setup\n");
+ printk("This costs you %d MB of RAM\n",
+ 32 << fallback_aper_order);
aper_order = fallback_aper_order;
aper_alloc = allocate_aperture();
- if (!aper_alloc) {
- /*
- * Could disable AGP and IOMMU here, but it's
- * probably not worth it. But the later users
- * cannot deal with bad apertures and turning
- * on the aperture over memory causes very
- * strange problems, so it's better to panic
- * early.
- */
+ if (!aper_alloc) {
+ /* Could disable AGP and IOMMU here, but it's probably
+ not worth it. But the later users cannot deal with
+ bad apertures and turning on the aperture over memory
+ causes very strange problems, so it's better to
+ panic early. */
panic("Not enough memory for aperture");
}
- } else {
- return;
- }
+ } else {
+ return;
+ }
/* Fix up the north bridges */
- for (num = 24; num < 32; num++) {
+ for (num = 24; num < 32; num++) {
if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
- continue;
-
- /*
- * Don't enable translation yet. That is done later.
- * Assume this BIOS didn't initialise the GART so
- * just overwrite all previous bits
- */
- write_pci_config(0, num, 3, 0x90, aper_order<<1);
- write_pci_config(0, num, 3, 0x94, aper_alloc>>25);
- }
-}
+ continue;
+
+ /* Don't enable translation yet. That is done later.
+ Assume this BIOS didn't initialise the GART so
+ just overwrite all previous bits */
+ write_pci_config(0, num, 3, 0x90, aper_order<<1);
+ write_pci_config(0, num, 3, 0x94, aper_alloc>>25);
+ }
+}
diff --git a/trunk/arch/x86/kernel/apic_32.c b/trunk/arch/x86/kernel/apic_32.c
index 35a568ea8400..a56c782653be 100644
--- a/trunk/arch/x86/kernel/apic_32.c
+++ b/trunk/arch/x86/kernel/apic_32.c
@@ -43,10 +43,12 @@
#include
#include
+#include "io_ports.h"
+
/*
* Sanity check
*/
-#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F)
+#if (SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F
# error SPURIOUS_APIC_VECTOR definition error
#endif
@@ -55,7 +57,7 @@
*
* -1=force-disable, +1=force-enable
*/
-static int enable_local_apic __initdata;
+static int enable_local_apic __initdata = 0;
/* Local APIC timer verification ok */
static int local_apic_timer_verify_ok;
@@ -99,8 +101,6 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
/* Local APIC was disabled by the BIOS and enabled by the kernel */
static int enabled_via_apicbase;
-static unsigned long apic_phys;
-
/*
* Get the LAPIC version
*/
@@ -110,7 +110,7 @@ static inline int lapic_get_version(void)
}
/*
- * Check, if the APIC is integrated or a separate chip
+ * Check, if the APIC is integrated or a seperate chip
*/
static inline int lapic_is_integrated(void)
{
@@ -135,9 +135,9 @@ void apic_wait_icr_idle(void)
cpu_relax();
}
-u32 safe_apic_wait_icr_idle(void)
+unsigned long safe_apic_wait_icr_idle(void)
{
- u32 send_status;
+ unsigned long send_status;
int timeout;
timeout = 0;
@@ -154,7 +154,7 @@ u32 safe_apic_wait_icr_idle(void)
/**
* enable_NMI_through_LVT0 - enable NMI through local vector table 0
*/
-void __cpuinit enable_NMI_through_LVT0(void)
+void enable_NMI_through_LVT0 (void * dummy)
{
unsigned int v = APIC_DM_NMI;
@@ -379,10 +379,8 @@ void __init setup_boot_APIC_clock(void)
*/
if (local_apic_timer_disabled) {
/* No broadcast on UP ! */
- if (num_possible_cpus() > 1) {
- lapic_clockevent.mult = 1;
+ if (num_possible_cpus() > 1)
setup_APIC_timer();
- }
return;
}
@@ -436,7 +434,7 @@ void __init setup_boot_APIC_clock(void)
"with PM Timer: %ldms instead of 100ms\n",
(long)res);
/* Correct the lapic counter value */
- res = (((u64) delta) * pm_100ms);
+ res = (((u64) delta ) * pm_100ms);
do_div(res, deltapm);
printk(KERN_INFO "APIC delta adjusted to PM-Timer: "
"%lu (%ld)\n", (unsigned long) res, delta);
@@ -474,19 +472,6 @@ void __init setup_boot_APIC_clock(void)
local_apic_timer_verify_ok = 1;
- /*
- * Do a sanity check on the APIC calibration result
- */
- if (calibration_result < (1000000 / HZ)) {
- local_irq_enable();
- printk(KERN_WARNING
- "APIC frequency too slow, disabling apic timer\n");
- /* No broadcast on UP ! */
- if (num_possible_cpus() > 1)
- setup_APIC_timer();
- return;
- }
-
/* We trust the pm timer based calibration */
if (!pm_referenced) {
apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
@@ -578,9 +563,6 @@ static void local_apic_timer_interrupt(void)
return;
}
- /*
- * the NMI deadlock-detector uses this.
- */
per_cpu(irq_stat, cpu).apic_timer_irqs++;
evt->event_handler(evt);
@@ -594,7 +576,8 @@ static void local_apic_timer_interrupt(void)
* [ if a single-CPU system runs an SMP kernel then we call the local
* interrupt as well. Thus we cannot inline the local irq ... ]
*/
-void smp_apic_timer_interrupt(struct pt_regs *regs)
+
+void fastcall smp_apic_timer_interrupt(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -633,14 +616,9 @@ int setup_profiling_timer(unsigned int multiplier)
*/
void clear_local_APIC(void)
{
- int maxlvt;
- u32 v;
-
- /* APIC hasn't been mapped yet */
- if (!apic_phys)
- return;
+ int maxlvt = lapic_get_maxlvt();
+ unsigned long v;
- maxlvt = lapic_get_maxlvt();
/*
* Masking an LVT entry can trigger a local APIC error
* if the vector is zero. Mask LVTERR first to prevent this.
@@ -998,8 +976,7 @@ void __cpuinit setup_local_APIC(void)
value |= APIC_LVT_LEVEL_TRIGGER;
apic_write_around(APIC_LVT1, value);
- if (integrated && !esr_disable) {
- /* !82489DX */
+ if (integrated && !esr_disable) { /* !82489DX */
maxlvt = lapic_get_maxlvt();
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
@@ -1043,7 +1020,7 @@ void __cpuinit setup_local_APIC(void)
/*
* Detect and initialize APIC
*/
-static int __init detect_init_APIC(void)
+static int __init detect_init_APIC (void)
{
u32 h, l, features;
@@ -1100,7 +1077,7 @@ static int __init detect_init_APIC(void)
printk(KERN_WARNING "Could not enable APIC!\n");
return -1;
}
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+ set_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
/* The BIOS may have set up the APIC at some other address */
@@ -1127,6 +1104,8 @@ static int __init detect_init_APIC(void)
*/
void __init init_apic_mappings(void)
{
+ unsigned long apic_phys;
+
/*
* If no local APIC can be found then set up a fake all
* zeroes page to simulate the local APIC and another
@@ -1185,10 +1164,10 @@ void __init init_apic_mappings(void)
* This initializes the IO-APIC and APIC hardware if this is
* a UP kernel.
*/
-int __init APIC_init_uniprocessor(void)
+int __init APIC_init_uniprocessor (void)
{
if (enable_local_apic < 0)
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+ clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
if (!smp_found_config && !cpu_has_apic)
return -1;
@@ -1200,7 +1179,7 @@ int __init APIC_init_uniprocessor(void)
APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
boot_cpu_physical_apicid);
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+ clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
return -1;
}
@@ -1230,6 +1209,50 @@ int __init APIC_init_uniprocessor(void)
return 0;
}
+/*
+ * APIC command line parameters
+ */
+static int __init parse_lapic(char *arg)
+{
+ enable_local_apic = 1;
+ return 0;
+}
+early_param("lapic", parse_lapic);
+
+static int __init parse_nolapic(char *arg)
+{
+ enable_local_apic = -1;
+ clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
+ return 0;
+}
+early_param("nolapic", parse_nolapic);
+
+static int __init parse_disable_lapic_timer(char *arg)
+{
+ local_apic_timer_disabled = 1;
+ return 0;
+}
+early_param("nolapic_timer", parse_disable_lapic_timer);
+
+static int __init parse_lapic_timer_c2_ok(char *arg)
+{
+ local_apic_timer_c2_ok = 1;
+ return 0;
+}
+early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
+
+static int __init apic_set_verbosity(char *str)
+{
+ if (strcmp("debug", str) == 0)
+ apic_verbosity = APIC_DEBUG;
+ else if (strcmp("verbose", str) == 0)
+ apic_verbosity = APIC_VERBOSE;
+ return 1;
+}
+
+__setup("apic=", apic_set_verbosity);
+
+
/*
* Local APIC interrupts
*/
@@ -1283,7 +1306,7 @@ void smp_error_interrupt(struct pt_regs *regs)
6: Received illegal vector
7: Illegal register address
*/
- printk(KERN_DEBUG "APIC error on CPU%d: %02lx(%02lx)\n",
+ printk (KERN_DEBUG "APIC error on CPU%d: %02lx(%02lx)\n",
smp_processor_id(), v , v1);
irq_exit();
}
@@ -1370,7 +1393,7 @@ void disconnect_bsp_APIC(int virt_wire_setup)
value = apic_read(APIC_LVT0);
value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
- APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
+ APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED );
value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
apic_write_around(APIC_LVT0, value);
@@ -1542,46 +1565,3 @@ device_initcall(init_lapic_sysfs);
static void apic_pm_activate(void) { }
#endif /* CONFIG_PM */
-
-/*
- * APIC command line parameters
- */
-static int __init parse_lapic(char *arg)
-{
- enable_local_apic = 1;
- return 0;
-}
-early_param("lapic", parse_lapic);
-
-static int __init parse_nolapic(char *arg)
-{
- enable_local_apic = -1;
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
- return 0;
-}
-early_param("nolapic", parse_nolapic);
-
-static int __init parse_disable_lapic_timer(char *arg)
-{
- local_apic_timer_disabled = 1;
- return 0;
-}
-early_param("nolapic_timer", parse_disable_lapic_timer);
-
-static int __init parse_lapic_timer_c2_ok(char *arg)
-{
- local_apic_timer_c2_ok = 1;
- return 0;
-}
-early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
-
-static int __init apic_set_verbosity(char *str)
-{
- if (strcmp("debug", str) == 0)
- apic_verbosity = APIC_DEBUG;
- else if (strcmp("verbose", str) == 0)
- apic_verbosity = APIC_VERBOSE;
- return 1;
-}
-__setup("apic=", apic_set_verbosity);
-
diff --git a/trunk/arch/x86/kernel/apic_64.c b/trunk/arch/x86/kernel/apic_64.c
index d8d03e09dea2..fa6cdee6d303 100644
--- a/trunk/arch/x86/kernel/apic_64.c
+++ b/trunk/arch/x86/kernel/apic_64.c
@@ -23,37 +23,32 @@
#include
#include
#include
+#include
#include
#include
-#include
-#include
#include
#include
#include
#include
-#include
#include
#include
#include
#include
#include
#include
+#include
#include
+int apic_verbosity;
int disable_apic_timer __cpuinitdata;
static int apic_calibrate_pmtmr __initdata;
-int disable_apic;
-/* Local APIC timer works in C2 */
+/* Local APIC timer works in C2? */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
-/*
- * Debug level, exported for io_apic.c
- */
-int apic_verbosity;
-
+static struct resource *ioapic_resources;
static struct resource lapic_resource = {
.name = "Local APIC",
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
@@ -65,8 +60,10 @@ static int lapic_next_event(unsigned long delta,
struct clock_event_device *evt);
static void lapic_timer_setup(enum clock_event_mode mode,
struct clock_event_device *evt);
+
static void lapic_timer_broadcast(cpumask_t mask);
-static void apic_pm_activate(void);
+
+static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen);
static struct clock_event_device lapic_clockevent = {
.name = "lapic",
@@ -81,45 +78,66 @@ static struct clock_event_device lapic_clockevent = {
};
static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
-static unsigned long apic_phys;
-
-/*
- * Get the LAPIC version
- */
-static inline int lapic_get_version(void)
+static int lapic_next_event(unsigned long delta,
+ struct clock_event_device *evt)
{
- return GET_APIC_VERSION(apic_read(APIC_LVR));
+ apic_write(APIC_TMICT, delta);
+ return 0;
}
-/*
- * Check, if the APIC is integrated or a seperate chip
- */
-static inline int lapic_is_integrated(void)
+static void lapic_timer_setup(enum clock_event_mode mode,
+ struct clock_event_device *evt)
{
- return 1;
+ unsigned long flags;
+ unsigned int v;
+
+ /* Lapic used as dummy for broadcast ? */
+ if (evt->features & CLOCK_EVT_FEAT_DUMMY)
+ return;
+
+ local_irq_save(flags);
+
+ switch (mode) {
+ case CLOCK_EVT_MODE_PERIODIC:
+ case CLOCK_EVT_MODE_ONESHOT:
+ __setup_APIC_LVTT(calibration_result,
+ mode != CLOCK_EVT_MODE_PERIODIC, 1);
+ break;
+ case CLOCK_EVT_MODE_UNUSED:
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ v = apic_read(APIC_LVTT);
+ v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+ apic_write(APIC_LVTT, v);
+ break;
+ case CLOCK_EVT_MODE_RESUME:
+ /* Nothing to do here */
+ break;
+ }
+
+ local_irq_restore(flags);
}
/*
- * Check, whether this is a modern or a first generation APIC
+ * Local APIC timer broadcast function
*/
-static int modern_apic(void)
+static void lapic_timer_broadcast(cpumask_t mask)
{
- /* AMD systems use old APIC versions, so check the CPU */
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
- boot_cpu_data.x86 >= 0xf)
- return 1;
- return lapic_get_version() >= 0x14;
+#ifdef CONFIG_SMP
+ send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
+#endif
}
+static void apic_pm_activate(void);
+
void apic_wait_icr_idle(void)
{
while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
cpu_relax();
}
-u32 safe_apic_wait_icr_idle(void)
+unsigned int safe_apic_wait_icr_idle(void)
{
- u32 send_status;
+ unsigned int send_status;
int timeout;
timeout = 0;
@@ -133,10 +151,7 @@ u32 safe_apic_wait_icr_idle(void)
return send_status;
}
-/**
- * enable_NMI_through_LVT0 - enable NMI through local vector table 0
- */
-void __cpuinit enable_NMI_through_LVT0(void)
+void enable_NMI_through_LVT0 (void * dummy)
{
unsigned int v;
@@ -145,10 +160,7 @@ void __cpuinit enable_NMI_through_LVT0(void)
apic_write(APIC_LVT0, v);
}
-/**
- * lapic_get_maxlvt - get the maximum number of local vector table entries
- */
-int lapic_get_maxlvt(void)
+int get_maxlvt(void)
{
unsigned int v, maxlvt;
@@ -158,484 +170,172 @@ int lapic_get_maxlvt(void)
}
/*
- * This function sets up the local APIC timer, with a timeout of
- * 'clocks' APIC bus clock. During calibration we actually call
- * this function twice on the boot CPU, once with a bogus timeout
- * value, second time for real. The other (noncalibrating) CPUs
- * call this function only once, with the real, calibrated value.
- *
- * We do reads before writes even if unnecessary, to get around the
- * P5 APIC double write bug.
+ * 'what should we do if we get a hw irq event on an illegal vector'.
+ * each architecture has to answer this themselves.
*/
-
-static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
+void ack_bad_irq(unsigned int irq)
{
- unsigned int lvtt_value, tmp_value;
+ printk("unexpected IRQ trap at vector %02x\n", irq);
+ /*
+ * Currently unexpected vectors happen only on SMP and APIC.
+ * We _must_ ack these because every local APIC has only N
+ * irq slots per priority level, and a 'hanging, unacked' IRQ
+ * holds up an irq slot - in excessive cases (when multiple
+ * unexpected vectors occur) that might lock up the APIC
+ * completely.
+ * But don't ack when the APIC is disabled. -AK
+ */
+ if (!disable_apic)
+ ack_APIC_irq();
+}
- lvtt_value = LOCAL_TIMER_VECTOR;
- if (!oneshot)
- lvtt_value |= APIC_LVT_TIMER_PERIODIC;
- if (!irqen)
- lvtt_value |= APIC_LVT_MASKED;
+void clear_local_APIC(void)
+{
+ int maxlvt;
+ unsigned int v;
- apic_write(APIC_LVTT, lvtt_value);
+ maxlvt = get_maxlvt();
/*
- * Divide PICLK by 16
+ * Masking an LVT entry can trigger a local APIC error
+ * if the vector is zero. Mask LVTERR first to prevent this.
*/
- tmp_value = apic_read(APIC_TDCR);
- apic_write(APIC_TDCR, (tmp_value
- & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
- | APIC_TDR_DIV_16);
+ if (maxlvt >= 3) {
+ v = ERROR_APIC_VECTOR; /* any non-zero vector will do */
+ apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
+ }
+ /*
+ * Careful: we have to set masks only first to deassert
+ * any level-triggered sources.
+ */
+ v = apic_read(APIC_LVTT);
+ apic_write(APIC_LVTT, v | APIC_LVT_MASKED);
+ v = apic_read(APIC_LVT0);
+ apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
+ v = apic_read(APIC_LVT1);
+ apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
+ if (maxlvt >= 4) {
+ v = apic_read(APIC_LVTPC);
+ apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
+ }
- if (!oneshot)
- apic_write(APIC_TMICT, clocks);
+ /*
+ * Clean APIC state for other OSs:
+ */
+ apic_write(APIC_LVTT, APIC_LVT_MASKED);
+ apic_write(APIC_LVT0, APIC_LVT_MASKED);
+ apic_write(APIC_LVT1, APIC_LVT_MASKED);
+ if (maxlvt >= 3)
+ apic_write(APIC_LVTERR, APIC_LVT_MASKED);
+ if (maxlvt >= 4)
+ apic_write(APIC_LVTPC, APIC_LVT_MASKED);
+ apic_write(APIC_ESR, 0);
+ apic_read(APIC_ESR);
}
-/*
- * Setup extended LVT, AMD specific (K8, family 10h)
- *
- * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
- * MCE interrupts are supported. Thus MCE offset must be set to 0.
- */
+void disconnect_bsp_APIC(int virt_wire_setup)
+{
+ /* Go back to Virtual Wire compatibility mode */
+ unsigned long value;
-#define APIC_EILVT_LVTOFF_MCE 0
-#define APIC_EILVT_LVTOFF_IBS 1
+ /* For the spurious interrupt use vector F, and enable it */
+ value = apic_read(APIC_SPIV);
+ value &= ~APIC_VECTOR_MASK;
+ value |= APIC_SPIV_APIC_ENABLED;
+ value |= 0xf;
+ apic_write(APIC_SPIV, value);
-static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
-{
- unsigned long reg = (lvt_off << 4) + APIC_EILVT0;
- unsigned int v = (mask << 16) | (msg_type << 8) | vector;
+ if (!virt_wire_setup) {
+ /*
+ * For LVT0 make it edge triggered, active high,
+ * external and enabled
+ */
+ value = apic_read(APIC_LVT0);
+ value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
+ APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
+ APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED );
+ value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
+ value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
+ apic_write(APIC_LVT0, value);
+ } else {
+ /* Disable LVT0 */
+ apic_write(APIC_LVT0, APIC_LVT_MASKED);
+ }
- apic_write(reg, v);
+ /* For LVT1 make it edge triggered, active high, nmi and enabled */
+ value = apic_read(APIC_LVT1);
+ value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
+ APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
+ APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
+ value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
+ value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
+ apic_write(APIC_LVT1, value);
}
-u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask)
+void disable_local_APIC(void)
{
- setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask);
- return APIC_EILVT_LVTOFF_MCE;
-}
+ unsigned int value;
-u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
-{
- setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
- return APIC_EILVT_LVTOFF_IBS;
-}
+ clear_local_APIC();
-/*
- * Program the next event, relative to now
- */
-static int lapic_next_event(unsigned long delta,
- struct clock_event_device *evt)
-{
- apic_write(APIC_TMICT, delta);
- return 0;
+ /*
+ * Disable APIC (implies clearing of registers
+ * for 82489DX!).
+ */
+ value = apic_read(APIC_SPIV);
+ value &= ~APIC_SPIV_APIC_ENABLED;
+ apic_write(APIC_SPIV, value);
}
-/*
- * Setup the lapic timer in periodic or oneshot mode
- */
-static void lapic_timer_setup(enum clock_event_mode mode,
- struct clock_event_device *evt)
+void lapic_shutdown(void)
{
unsigned long flags;
- unsigned int v;
- /* Lapic used as dummy for broadcast ? */
- if (evt->features & CLOCK_EVT_FEAT_DUMMY)
+ if (!cpu_has_apic)
return;
local_irq_save(flags);
- switch (mode) {
- case CLOCK_EVT_MODE_PERIODIC:
- case CLOCK_EVT_MODE_ONESHOT:
- __setup_APIC_LVTT(calibration_result,
- mode != CLOCK_EVT_MODE_PERIODIC, 1);
- break;
- case CLOCK_EVT_MODE_UNUSED:
- case CLOCK_EVT_MODE_SHUTDOWN:
- v = apic_read(APIC_LVTT);
- v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
- apic_write(APIC_LVTT, v);
- break;
- case CLOCK_EVT_MODE_RESUME:
- /* Nothing to do here */
- break;
- }
+ disable_local_APIC();
local_irq_restore(flags);
}
/*
- * Local APIC timer broadcast function
+ * This is to verify that we're looking at a real local APIC.
+ * Check these against your board if the CPUs aren't getting
+ * started for no apparent reason.
*/
-static void lapic_timer_broadcast(cpumask_t mask)
+int __init verify_local_APIC(void)
{
-#ifdef CONFIG_SMP
- send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
-#endif
-}
+ unsigned int reg0, reg1;
-/*
- * Setup the local APIC timer for this CPU. Copy the initilized values
- * of the boot CPU and register the clock event in the framework.
- */
-static void setup_APIC_timer(void)
-{
- struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+ /*
+ * The version register is read-only in a real APIC.
+ */
+ reg0 = apic_read(APIC_LVR);
+ apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0);
+ apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK);
+ reg1 = apic_read(APIC_LVR);
+ apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1);
- memcpy(levt, &lapic_clockevent, sizeof(*levt));
- levt->cpumask = cpumask_of_cpu(smp_processor_id());
+ /*
+ * The two version reads above should print the same
+ * numbers. If the second one is different, then we
+ * poke at a non-APIC.
+ */
+ if (reg1 != reg0)
+ return 0;
- clockevents_register_device(levt);
-}
-
-/*
- * In this function we calibrate APIC bus clocks to the external
- * timer. Unfortunately we cannot use jiffies and the timer irq
- * to calibrate, since some later bootup code depends on getting
- * the first irq? Ugh.
- *
- * We want to do the calibration only once since we
- * want to have local timer irqs syncron. CPUs connected
- * by the same APIC bus have the very same bus frequency.
- * And we want to have irqs off anyways, no accidental
- * APIC irq that way.
- */
-
-#define TICK_COUNT 100000000
-
-static void __init calibrate_APIC_clock(void)
-{
- unsigned apic, apic_start;
- unsigned long tsc, tsc_start;
- int result;
-
- local_irq_disable();
-
- /*
- * Put whatever arbitrary (but long enough) timeout
- * value into the APIC clock, we just want to get the
- * counter running for calibration.
- *
- * No interrupt enable !
- */
- __setup_APIC_LVTT(250000000, 0, 0);
-
- apic_start = apic_read(APIC_TMCCT);
-#ifdef CONFIG_X86_PM_TIMER
- if (apic_calibrate_pmtmr && pmtmr_ioport) {
- pmtimer_wait(5000); /* 5ms wait */
- apic = apic_read(APIC_TMCCT);
- result = (apic_start - apic) * 1000L / 5;
- } else
-#endif
- {
- rdtscll(tsc_start);
-
- do {
- apic = apic_read(APIC_TMCCT);
- rdtscll(tsc);
- } while ((tsc - tsc_start) < TICK_COUNT &&
- (apic_start - apic) < TICK_COUNT);
-
- result = (apic_start - apic) * 1000L * tsc_khz /
- (tsc - tsc_start);
- }
-
- local_irq_enable();
-
- printk(KERN_DEBUG "APIC timer calibration result %d\n", result);
-
- printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n",
- result / 1000 / 1000, result / 1000 % 1000);
-
- /* Calculate the scaled math multiplication factor */
- lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32);
- lapic_clockevent.max_delta_ns =
- clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
- lapic_clockevent.min_delta_ns =
- clockevent_delta2ns(0xF, &lapic_clockevent);
-
- calibration_result = result / HZ;
-}
-
-/*
- * Setup the boot APIC
- *
- * Calibrate and verify the result.
- */
-void __init setup_boot_APIC_clock(void)
-{
- /*
- * The local apic timer can be disabled via the kernel commandline.
- * Register the lapic timer as a dummy clock event source on SMP
- * systems, so the broadcast mechanism is used. On UP systems simply
- * ignore it.
- */
- if (disable_apic_timer) {
- printk(KERN_INFO "Disabling APIC timer\n");
- /* No broadcast on UP ! */
- if (num_possible_cpus() > 1) {
- lapic_clockevent.mult = 1;
- setup_APIC_timer();
- }
- return;
- }
-
- printk(KERN_INFO "Using local APIC timer interrupts.\n");
- calibrate_APIC_clock();
-
- /*
- * Do a sanity check on the APIC calibration result
- */
- if (calibration_result < (1000000 / HZ)) {
- printk(KERN_WARNING
- "APIC frequency too slow, disabling apic timer\n");
- /* No broadcast on UP ! */
- if (num_possible_cpus() > 1)
- setup_APIC_timer();
- return;
- }
-
- /*
- * If nmi_watchdog is set to IO_APIC, we need the
- * PIT/HPET going. Otherwise register lapic as a dummy
- * device.
- */
- if (nmi_watchdog != NMI_IO_APIC)
- lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
- else
- printk(KERN_WARNING "APIC timer registered as dummy,"
- " due to nmi_watchdog=1!\n");
-
- setup_APIC_timer();
-}
-
-/*
- * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
- * C1E flag only in the secondary CPU, so when we detect the wreckage
- * we already have enabled the boot CPU local apic timer. Check, if
- * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
- * set the DUMMY flag again and force the broadcast mode in the
- * clockevents layer.
- */
-void __cpuinit check_boot_apic_timer_broadcast(void)
-{
- if (!disable_apic_timer ||
- (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
- return;
-
- printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
- lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
-
- local_irq_enable();
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &boot_cpu_id);
- local_irq_disable();
-}
-
-void __cpuinit setup_secondary_APIC_clock(void)
-{
- check_boot_apic_timer_broadcast();
- setup_APIC_timer();
-}
-
-/*
- * The guts of the apic timer interrupt
- */
-static void local_apic_timer_interrupt(void)
-{
- int cpu = smp_processor_id();
- struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
-
- /*
- * Normally we should not be here till LAPIC has been initialized but
- * in some cases like kdump, its possible that there is a pending LAPIC
- * timer interrupt from previous kernel's context and is delivered in
- * new kernel the moment interrupts are enabled.
- *
- * Interrupts are enabled early and LAPIC is setup much later, hence
- * its possible that when we get here evt->event_handler is NULL.
- * Check for event_handler being NULL and discard the interrupt as
- * spurious.
- */
- if (!evt->event_handler) {
- printk(KERN_WARNING
- "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
- /* Switch it off */
- lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
- return;
- }
-
- /*
- * the NMI deadlock-detector uses this.
- */
- add_pda(apic_timer_irqs, 1);
-
- evt->event_handler(evt);
-}
-
-/*
- * Local APIC timer interrupt. This is the most natural way for doing
- * local interrupts, but local timer interrupts can be emulated by
- * broadcast interrupts too. [in case the hw doesn't support APIC timers]
- *
- * [ if a single-CPU system runs an SMP kernel then we call the local
- * interrupt as well. Thus we cannot inline the local irq ... ]
- */
-void smp_apic_timer_interrupt(struct pt_regs *regs)
-{
- struct pt_regs *old_regs = set_irq_regs(regs);
-
- /*
- * NOTE! We'd better ACK the irq immediately,
- * because timer handling can be slow.
- */
- ack_APIC_irq();
- /*
- * update_process_times() expects us to have done irq_enter().
- * Besides, if we don't timer interrupts ignore the global
- * interrupt lock, which is the WrongThing (tm) to do.
- */
- exit_idle();
- irq_enter();
- local_apic_timer_interrupt();
- irq_exit();
- set_irq_regs(old_regs);
-}
-
-int setup_profiling_timer(unsigned int multiplier)
-{
- return -EINVAL;
-}
-
-
-/*
- * Local APIC start and shutdown
- */
-
-/**
- * clear_local_APIC - shutdown the local APIC
- *
- * This is called, when a CPU is disabled and before rebooting, so the state of
- * the local APIC has no dangling leftovers. Also used to cleanout any BIOS
- * leftovers during boot.
- */
-void clear_local_APIC(void)
-{
- int maxlvt = lapic_get_maxlvt();
- u32 v;
-
- /* APIC hasn't been mapped yet */
- if (!apic_phys)
- return;
-
- maxlvt = lapic_get_maxlvt();
- /*
- * Masking an LVT entry can trigger a local APIC error
- * if the vector is zero. Mask LVTERR first to prevent this.
- */
- if (maxlvt >= 3) {
- v = ERROR_APIC_VECTOR; /* any non-zero vector will do */
- apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
- }
- /*
- * Careful: we have to set masks only first to deassert
- * any level-triggered sources.
- */
- v = apic_read(APIC_LVTT);
- apic_write(APIC_LVTT, v | APIC_LVT_MASKED);
- v = apic_read(APIC_LVT0);
- apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
- v = apic_read(APIC_LVT1);
- apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
- if (maxlvt >= 4) {
- v = apic_read(APIC_LVTPC);
- apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
- }
-
- /*
- * Clean APIC state for other OSs:
- */
- apic_write(APIC_LVTT, APIC_LVT_MASKED);
- apic_write(APIC_LVT0, APIC_LVT_MASKED);
- apic_write(APIC_LVT1, APIC_LVT_MASKED);
- if (maxlvt >= 3)
- apic_write(APIC_LVTERR, APIC_LVT_MASKED);
- if (maxlvt >= 4)
- apic_write(APIC_LVTPC, APIC_LVT_MASKED);
- apic_write(APIC_ESR, 0);
- apic_read(APIC_ESR);
-}
-
-/**
- * disable_local_APIC - clear and disable the local APIC
- */
-void disable_local_APIC(void)
-{
- unsigned int value;
-
- clear_local_APIC();
-
- /*
- * Disable APIC (implies clearing of registers
- * for 82489DX!).
- */
- value = apic_read(APIC_SPIV);
- value &= ~APIC_SPIV_APIC_ENABLED;
- apic_write(APIC_SPIV, value);
-}
-
-void lapic_shutdown(void)
-{
- unsigned long flags;
-
- if (!cpu_has_apic)
- return;
-
- local_irq_save(flags);
-
- disable_local_APIC();
-
- local_irq_restore(flags);
-}
-
-/*
- * This is to verify that we're looking at a real local APIC.
- * Check these against your board if the CPUs aren't getting
- * started for no apparent reason.
- */
-int __init verify_local_APIC(void)
-{
- unsigned int reg0, reg1;
-
- /*
- * The version register is read-only in a real APIC.
- */
- reg0 = apic_read(APIC_LVR);
- apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0);
- apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK);
- reg1 = apic_read(APIC_LVR);
- apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1);
-
- /*
- * The two version reads above should print the same
- * numbers. If the second one is different, then we
- * poke at a non-APIC.
- */
- if (reg1 != reg0)
- return 0;
-
- /*
- * Check if the version looks reasonably.
- */
- reg1 = GET_APIC_VERSION(reg0);
- if (reg1 == 0x00 || reg1 == 0xff)
- return 0;
- reg1 = lapic_get_maxlvt();
- if (reg1 < 0x02 || reg1 == 0xff)
- return 0;
+ /*
+ * Check if the version looks reasonably.
+ */
+ reg1 = GET_APIC_VERSION(reg0);
+ if (reg1 == 0x00 || reg1 == 0xff)
+ return 0;
+ reg1 = get_maxlvt();
+ if (reg1 < 0x02 || reg1 == 0xff)
+ return 0;
/*
* The ID register is read/write in a real APIC.
@@ -655,20 +355,18 @@ int __init verify_local_APIC(void)
* compatibility mode, but most boxes are anymore.
*/
reg0 = apic_read(APIC_LVT0);
- apic_printk(APIC_DEBUG, "Getting LVT0: %x\n", reg0);
+ apic_printk(APIC_DEBUG,"Getting LVT0: %x\n", reg0);
reg1 = apic_read(APIC_LVT1);
apic_printk(APIC_DEBUG, "Getting LVT1: %x\n", reg1);
return 1;
}
-/**
- * sync_Arb_IDs - synchronize APIC bus arbitration IDs
- */
void __init sync_Arb_IDs(void)
{
/* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */
- if (modern_apic())
+ unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
+ if (ver >= 0x14) /* P4 or higher */
return;
/*
@@ -720,12 +418,9 @@ void __init init_bsp_APIC(void)
apic_write(APIC_LVT1, value);
}
-/**
- * setup_local_APIC - setup the local APIC
- */
-void __cpuinit setup_local_APIC(void)
+void __cpuinit setup_local_APIC (void)
{
- unsigned int value;
+ unsigned int value, maxlvt;
int i, j;
value = apic_read(APIC_LVR);
@@ -821,27 +516,183 @@ void __cpuinit setup_local_APIC(void)
else
value = APIC_DM_NMI | APIC_LVT_MASKED;
apic_write(APIC_LVT1, value);
+
+ {
+ unsigned oldvalue;
+ maxlvt = get_maxlvt();
+ oldvalue = apic_read(APIC_ESR);
+ value = ERROR_APIC_VECTOR; // enables sending errors
+ apic_write(APIC_LVTERR, value);
+ /*
+ * spec says clear errors after enabling vector.
+ */
+ if (maxlvt > 3)
+ apic_write(APIC_ESR, 0);
+ value = apic_read(APIC_ESR);
+ if (value != oldvalue)
+ apic_printk(APIC_VERBOSE,
+ "ESR value after enabling vector: %08x, after %08x\n",
+ oldvalue, value);
+ }
+
+ nmi_watchdog_default();
+ setup_apic_nmi_watchdog(NULL);
+ apic_pm_activate();
}
-void __cpuinit lapic_setup_esr(void)
+#ifdef CONFIG_PM
+
+static struct {
+ /* 'active' is true if the local APIC was enabled by us and
+ not the BIOS; this signifies that we are also responsible
+ for disabling it before entering apm/acpi suspend */
+ int active;
+ /* r/w apic fields */
+ unsigned int apic_id;
+ unsigned int apic_taskpri;
+ unsigned int apic_ldr;
+ unsigned int apic_dfr;
+ unsigned int apic_spiv;
+ unsigned int apic_lvtt;
+ unsigned int apic_lvtpc;
+ unsigned int apic_lvt0;
+ unsigned int apic_lvt1;
+ unsigned int apic_lvterr;
+ unsigned int apic_tmict;
+ unsigned int apic_tdcr;
+ unsigned int apic_thmr;
+} apic_pm_state;
+
+static int lapic_suspend(struct sys_device *dev, pm_message_t state)
{
- unsigned maxlvt = lapic_get_maxlvt();
+ unsigned long flags;
+ int maxlvt;
- apic_write(APIC_LVTERR, ERROR_APIC_VECTOR);
- /*
- * spec says clear errors after enabling vector.
- */
- if (maxlvt > 3)
- apic_write(APIC_ESR, 0);
+ if (!apic_pm_state.active)
+ return 0;
+
+ maxlvt = get_maxlvt();
+
+ apic_pm_state.apic_id = apic_read(APIC_ID);
+ apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
+ apic_pm_state.apic_ldr = apic_read(APIC_LDR);
+ apic_pm_state.apic_dfr = apic_read(APIC_DFR);
+ apic_pm_state.apic_spiv = apic_read(APIC_SPIV);
+ apic_pm_state.apic_lvtt = apic_read(APIC_LVTT);
+ if (maxlvt >= 4)
+ apic_pm_state.apic_lvtpc = apic_read(APIC_LVTPC);
+ apic_pm_state.apic_lvt0 = apic_read(APIC_LVT0);
+ apic_pm_state.apic_lvt1 = apic_read(APIC_LVT1);
+ apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
+ apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
+ apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
+#ifdef CONFIG_X86_MCE_INTEL
+ if (maxlvt >= 5)
+ apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
+#endif
+ local_irq_save(flags);
+ disable_local_APIC();
+ local_irq_restore(flags);
+ return 0;
}
-void __cpuinit end_local_APIC_setup(void)
+static int lapic_resume(struct sys_device *dev)
{
- lapic_setup_esr();
- nmi_watchdog_default();
- setup_apic_nmi_watchdog(NULL);
- apic_pm_activate();
+ unsigned int l, h;
+ unsigned long flags;
+ int maxlvt;
+
+ if (!apic_pm_state.active)
+ return 0;
+
+ maxlvt = get_maxlvt();
+
+ local_irq_save(flags);
+ rdmsr(MSR_IA32_APICBASE, l, h);
+ l &= ~MSR_IA32_APICBASE_BASE;
+ l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+ wrmsr(MSR_IA32_APICBASE, l, h);
+ apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
+ apic_write(APIC_ID, apic_pm_state.apic_id);
+ apic_write(APIC_DFR, apic_pm_state.apic_dfr);
+ apic_write(APIC_LDR, apic_pm_state.apic_ldr);
+ apic_write(APIC_TASKPRI, apic_pm_state.apic_taskpri);
+ apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
+ apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
+ apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
+#ifdef CONFIG_X86_MCE_INTEL
+ if (maxlvt >= 5)
+ apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
+#endif
+ if (maxlvt >= 4)
+ apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
+ apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
+ apic_write(APIC_TDCR, apic_pm_state.apic_tdcr);
+ apic_write(APIC_TMICT, apic_pm_state.apic_tmict);
+ apic_write(APIC_ESR, 0);
+ apic_read(APIC_ESR);
+ apic_write(APIC_LVTERR, apic_pm_state.apic_lvterr);
+ apic_write(APIC_ESR, 0);
+ apic_read(APIC_ESR);
+ local_irq_restore(flags);
+ return 0;
+}
+
+static struct sysdev_class lapic_sysclass = {
+ .name = "lapic",
+ .resume = lapic_resume,
+ .suspend = lapic_suspend,
+};
+
+static struct sys_device device_lapic = {
+ .id = 0,
+ .cls = &lapic_sysclass,
+};
+
+static void __cpuinit apic_pm_activate(void)
+{
+ apic_pm_state.active = 1;
+}
+
+static int __init init_lapic_sysfs(void)
+{
+ int error;
+ if (!cpu_has_apic)
+ return 0;
+ /* XXX: remove suspend/resume procs if !apic_pm_state.active? */
+ error = sysdev_class_register(&lapic_sysclass);
+ if (!error)
+ error = sysdev_register(&device_lapic);
+ return error;
+}
+device_initcall(init_lapic_sysfs);
+
+#else /* CONFIG_PM */
+
+static void apic_pm_activate(void) { }
+
+#endif /* CONFIG_PM */
+
+static int __init apic_set_verbosity(char *str)
+{
+ if (str == NULL) {
+ skip_ioapic_setup = 0;
+ ioapic_force = 1;
+ return 0;
+ }
+ if (strcmp("debug", str) == 0)
+ apic_verbosity = APIC_DEBUG;
+ else if (strcmp("verbose", str) == 0)
+ apic_verbosity = APIC_VERBOSE;
+ else {
+ printk(KERN_WARNING "APIC Verbosity level %s not recognised"
+ " use apic=verbose or apic=debug\n", str);
+ return -EINVAL;
+ }
+
+ return 0;
}
+early_param("apic", apic_set_verbosity);
/*
* Detect and enable local APICs on non-SMP boards.
@@ -849,7 +700,8 @@ void __cpuinit end_local_APIC_setup(void)
* On AMD64 we trust the BIOS - if it says no APIC it is likely
* not correctly set up (usually the APIC timer won't work etc.)
*/
-static int __init detect_init_APIC(void)
+
+static int __init detect_init_APIC (void)
{
if (!cpu_has_apic) {
printk(KERN_INFO "No local APIC present\n");
@@ -861,11 +713,68 @@ static int __init detect_init_APIC(void)
return 0;
}
-/**
- * init_apic_mappings - initialize APIC mappings
- */
+#ifdef CONFIG_X86_IO_APIC
+static struct resource * __init ioapic_setup_resources(void)
+{
+#define IOAPIC_RESOURCE_NAME_SIZE 11
+ unsigned long n;
+ struct resource *res;
+ char *mem;
+ int i;
+
+ if (nr_ioapics <= 0)
+ return NULL;
+
+ n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
+ n *= nr_ioapics;
+
+ mem = alloc_bootmem(n);
+ res = (void *)mem;
+
+ if (mem != NULL) {
+ memset(mem, 0, n);
+ mem += sizeof(struct resource) * nr_ioapics;
+
+ for (i = 0; i < nr_ioapics; i++) {
+ res[i].name = mem;
+ res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ sprintf(mem, "IOAPIC %u", i);
+ mem += IOAPIC_RESOURCE_NAME_SIZE;
+ }
+ }
+
+ ioapic_resources = res;
+
+ return res;
+}
+
+static int __init ioapic_insert_resources(void)
+{
+ int i;
+ struct resource *r = ioapic_resources;
+
+ if (!r) {
+ printk("IO APIC resources could be not be allocated.\n");
+ return -1;
+ }
+
+ for (i = 0; i < nr_ioapics; i++) {
+ insert_resource(&iomem_resource, r);
+ r++;
+ }
+
+ return 0;
+}
+
+/* Insert the IO APIC resources after PCI initialization has occured to handle
+ * IO APICS that are mapped in on a BAR in PCI space. */
+late_initcall(ioapic_insert_resources);
+#endif
+
void __init init_apic_mappings(void)
{
+ unsigned long apic_phys;
+
/*
* If no local APIC can be found then set up a fake all
* zeroes page to simulate the local APIC and another
@@ -891,281 +800,295 @@ void __init init_apic_mappings(void)
* default configuration (or the MP table is broken).
*/
boot_cpu_id = GET_APIC_ID(apic_read(APIC_ID));
+
+ {
+ unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
+ int i;
+ struct resource *ioapic_res;
+
+ ioapic_res = ioapic_setup_resources();
+ for (i = 0; i < nr_ioapics; i++) {
+ if (smp_found_config) {
+ ioapic_phys = mp_ioapics[i].mpc_apicaddr;
+ } else {
+ ioapic_phys = (unsigned long)
+ alloc_bootmem_pages(PAGE_SIZE);
+ ioapic_phys = __pa(ioapic_phys);
+ }
+ set_fixmap_nocache(idx, ioapic_phys);
+ apic_printk(APIC_VERBOSE,
+ "mapped IOAPIC to %016lx (%016lx)\n",
+ __fix_to_virt(idx), ioapic_phys);
+ idx++;
+
+ if (ioapic_res != NULL) {
+ ioapic_res->start = ioapic_phys;
+ ioapic_res->end = ioapic_phys + (4 * 1024) - 1;
+ ioapic_res++;
+ }
+ }
+ }
}
/*
- * This initializes the IO-APIC and APIC hardware if this is
- * a UP kernel.
+ * This function sets up the local APIC timer, with a timeout of
+ * 'clocks' APIC bus clock. During calibration we actually call
+ * this function twice on the boot CPU, once with a bogus timeout
+ * value, second time for real. The other (noncalibrating) CPUs
+ * call this function only once, with the real, calibrated value.
+ *
+ * We do reads before writes even if unnecessary, to get around the
+ * P5 APIC double write bug.
*/
-int __init APIC_init_uniprocessor(void)
-{
- if (disable_apic) {
- printk(KERN_INFO "Apic disabled\n");
- return -1;
- }
- if (!cpu_has_apic) {
- disable_apic = 1;
- printk(KERN_INFO "Apic disabled by BIOS\n");
- return -1;
- }
- verify_local_APIC();
+static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
+{
+ unsigned int lvtt_value, tmp_value;
- phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
- apic_write(APIC_ID, SET_APIC_ID(boot_cpu_id));
+ lvtt_value = LOCAL_TIMER_VECTOR;
+ if (!oneshot)
+ lvtt_value |= APIC_LVT_TIMER_PERIODIC;
+ if (!irqen)
+ lvtt_value |= APIC_LVT_MASKED;
- setup_local_APIC();
+ apic_write(APIC_LVTT, lvtt_value);
/*
- * Now enable IO-APICs, actually call clear_IO_APIC
- * We need clear_IO_APIC before enabling vector on BP
+ * Divide PICLK by 16
*/
- if (!skip_ioapic_setup && nr_ioapics)
- enable_IO_APIC();
-
- end_local_APIC_setup();
+ tmp_value = apic_read(APIC_TDCR);
+ apic_write(APIC_TDCR, (tmp_value
+ & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
+ | APIC_TDR_DIV_16);
- if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
- setup_IO_APIC();
- else
- nr_ioapics = 0;
- setup_boot_APIC_clock();
- check_nmi_watchdog();
- return 0;
+ if (!oneshot)
+ apic_write(APIC_TMICT, clocks);
}
-/*
- * Local APIC interrupts
- */
-
-/*
- * This interrupt should _never_ happen with our APIC/SMP architecture
- */
-asmlinkage void smp_spurious_interrupt(void)
+static void setup_APIC_timer(void)
{
- unsigned int v;
- exit_idle();
- irq_enter();
- /*
- * Check if this really is a spurious interrupt and ACK it
- * if it is a vectored one. Just in case...
- * Spurious interrupts should not be ACKed.
- */
- v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
- if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
- ack_APIC_irq();
+ struct clock_event_device *levt = &__get_cpu_var(lapic_events);
- add_pda(irq_spurious_count, 1);
- irq_exit();
+ memcpy(levt, &lapic_clockevent, sizeof(*levt));
+ levt->cpumask = cpumask_of_cpu(smp_processor_id());
+
+ clockevents_register_device(levt);
}
/*
- * This interrupt should never happen with our APIC/SMP architecture
+ * In this function we calibrate APIC bus clocks to the external
+ * timer. Unfortunately we cannot use jiffies and the timer irq
+ * to calibrate, since some later bootup code depends on getting
+ * the first irq? Ugh.
+ *
+ * We want to do the calibration only once since we
+ * want to have local timer irqs syncron. CPUs connected
+ * by the same APIC bus have the very same bus frequency.
+ * And we want to have irqs off anyways, no accidental
+ * APIC irq that way.
*/
-asmlinkage void smp_error_interrupt(void)
+
+#define TICK_COUNT 100000000
+
+static void __init calibrate_APIC_clock(void)
{
- unsigned int v, v1;
+ unsigned apic, apic_start;
+ unsigned long tsc, tsc_start;
+ int result;
- exit_idle();
- irq_enter();
- /* First tickle the hardware, only then report what went on. -- REW */
- v = apic_read(APIC_ESR);
- apic_write(APIC_ESR, 0);
- v1 = apic_read(APIC_ESR);
- ack_APIC_irq();
- atomic_inc(&irq_err_count);
+ local_irq_disable();
- /* Here is what the APIC error bits mean:
- 0: Send CS error
- 1: Receive CS error
- 2: Send accept error
- 3: Receive accept error
- 4: Reserved
- 5: Send illegal vector
- 6: Received illegal vector
- 7: Illegal register address
- */
- printk(KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
- smp_processor_id(), v , v1);
- irq_exit();
-}
+ /*
+ * Put whatever arbitrary (but long enough) timeout
+ * value into the APIC clock, we just want to get the
+ * counter running for calibration.
+ *
+ * No interrupt enable !
+ */
+ __setup_APIC_LVTT(250000000, 0, 0);
-void disconnect_bsp_APIC(int virt_wire_setup)
-{
- /* Go back to Virtual Wire compatibility mode */
- unsigned long value;
+ apic_start = apic_read(APIC_TMCCT);
+#ifdef CONFIG_X86_PM_TIMER
+ if (apic_calibrate_pmtmr && pmtmr_ioport) {
+ pmtimer_wait(5000); /* 5ms wait */
+ apic = apic_read(APIC_TMCCT);
+ result = (apic_start - apic) * 1000L / 5;
+ } else
+#endif
+ {
+ rdtscll(tsc_start);
- /* For the spurious interrupt use vector F, and enable it */
- value = apic_read(APIC_SPIV);
- value &= ~APIC_VECTOR_MASK;
- value |= APIC_SPIV_APIC_ENABLED;
- value |= 0xf;
- apic_write(APIC_SPIV, value);
+ do {
+ apic = apic_read(APIC_TMCCT);
+ rdtscll(tsc);
+ } while ((tsc - tsc_start) < TICK_COUNT &&
+ (apic_start - apic) < TICK_COUNT);
- if (!virt_wire_setup) {
- /*
- * For LVT0 make it edge triggered, active high,
- * external and enabled
- */
- value = apic_read(APIC_LVT0);
- value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
- APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
- APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
- value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
- value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
- apic_write(APIC_LVT0, value);
- } else {
- /* Disable LVT0 */
- apic_write(APIC_LVT0, APIC_LVT_MASKED);
+ result = (apic_start - apic) * 1000L * tsc_khz /
+ (tsc - tsc_start);
}
- /* For LVT1 make it edge triggered, active high, nmi and enabled */
- value = apic_read(APIC_LVT1);
- value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
- APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
- APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
- value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
- value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
- apic_write(APIC_LVT1, value);
-}
-
-/*
- * Power management
- */
-#ifdef CONFIG_PM
+ local_irq_enable();
-static struct {
- /* 'active' is true if the local APIC was enabled by us and
- not the BIOS; this signifies that we are also responsible
- for disabling it before entering apm/acpi suspend */
- int active;
- /* r/w apic fields */
- unsigned int apic_id;
- unsigned int apic_taskpri;
- unsigned int apic_ldr;
- unsigned int apic_dfr;
- unsigned int apic_spiv;
- unsigned int apic_lvtt;
- unsigned int apic_lvtpc;
- unsigned int apic_lvt0;
- unsigned int apic_lvt1;
- unsigned int apic_lvterr;
- unsigned int apic_tmict;
- unsigned int apic_tdcr;
- unsigned int apic_thmr;
-} apic_pm_state;
+ printk(KERN_DEBUG "APIC timer calibration result %d\n", result);
-static int lapic_suspend(struct sys_device *dev, pm_message_t state)
-{
- unsigned long flags;
- int maxlvt;
+ printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n",
+ result / 1000 / 1000, result / 1000 % 1000);
- if (!apic_pm_state.active)
- return 0;
+ /* Calculate the scaled math multiplication factor */
+ lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32);
+ lapic_clockevent.max_delta_ns =
+ clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ns =
+ clockevent_delta2ns(0xF, &lapic_clockevent);
- maxlvt = lapic_get_maxlvt();
+ calibration_result = result / HZ;
+}
- apic_pm_state.apic_id = apic_read(APIC_ID);
- apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
- apic_pm_state.apic_ldr = apic_read(APIC_LDR);
- apic_pm_state.apic_dfr = apic_read(APIC_DFR);
- apic_pm_state.apic_spiv = apic_read(APIC_SPIV);
- apic_pm_state.apic_lvtt = apic_read(APIC_LVTT);
- if (maxlvt >= 4)
- apic_pm_state.apic_lvtpc = apic_read(APIC_LVTPC);
- apic_pm_state.apic_lvt0 = apic_read(APIC_LVT0);
- apic_pm_state.apic_lvt1 = apic_read(APIC_LVT1);
- apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
- apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
- apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
-#ifdef CONFIG_X86_MCE_INTEL
- if (maxlvt >= 5)
- apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
-#endif
- local_irq_save(flags);
- disable_local_APIC();
- local_irq_restore(flags);
- return 0;
+void __init setup_boot_APIC_clock (void)
+{
+ /*
+ * The local apic timer can be disabled via the kernel commandline.
+ * Register the lapic timer as a dummy clock event source on SMP
+ * systems, so the broadcast mechanism is used. On UP systems simply
+ * ignore it.
+ */
+ if (disable_apic_timer) {
+ printk(KERN_INFO "Disabling APIC timer\n");
+ /* No broadcast on UP ! */
+ if (num_possible_cpus() > 1)
+ setup_APIC_timer();
+ return;
+ }
+
+ printk(KERN_INFO "Using local APIC timer interrupts.\n");
+ calibrate_APIC_clock();
+
+ /*
+ * If nmi_watchdog is set to IO_APIC, we need the
+ * PIT/HPET going. Otherwise register lapic as a dummy
+ * device.
+ */
+ if (nmi_watchdog != NMI_IO_APIC)
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+ else
+ printk(KERN_WARNING "APIC timer registered as dummy,"
+ " due to nmi_watchdog=1!\n");
+
+ setup_APIC_timer();
}
-static int lapic_resume(struct sys_device *dev)
+/*
+ * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
+ * C1E flag only in the secondary CPU, so when we detect the wreckage
+ * we already have enabled the boot CPU local apic timer. Check, if
+ * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
+ * set the DUMMY flag again and force the broadcast mode in the
+ * clockevents layer.
+ */
+void __cpuinit check_boot_apic_timer_broadcast(void)
{
- unsigned int l, h;
- unsigned long flags;
- int maxlvt;
-
- if (!apic_pm_state.active)
- return 0;
+ if (!disable_apic_timer ||
+ (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
+ return;
- maxlvt = lapic_get_maxlvt();
+ printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
+ lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
- local_irq_save(flags);
- rdmsr(MSR_IA32_APICBASE, l, h);
- l &= ~MSR_IA32_APICBASE_BASE;
- l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
- wrmsr(MSR_IA32_APICBASE, l, h);
- apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
- apic_write(APIC_ID, apic_pm_state.apic_id);
- apic_write(APIC_DFR, apic_pm_state.apic_dfr);
- apic_write(APIC_LDR, apic_pm_state.apic_ldr);
- apic_write(APIC_TASKPRI, apic_pm_state.apic_taskpri);
- apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
- apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
- apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
-#ifdef CONFIG_X86_MCE_INTEL
- if (maxlvt >= 5)
- apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
-#endif
- if (maxlvt >= 4)
- apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
- apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
- apic_write(APIC_TDCR, apic_pm_state.apic_tdcr);
- apic_write(APIC_TMICT, apic_pm_state.apic_tmict);
- apic_write(APIC_ESR, 0);
- apic_read(APIC_ESR);
- apic_write(APIC_LVTERR, apic_pm_state.apic_lvterr);
- apic_write(APIC_ESR, 0);
- apic_read(APIC_ESR);
- local_irq_restore(flags);
- return 0;
+ local_irq_enable();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &boot_cpu_id);
+ local_irq_disable();
}
-static struct sysdev_class lapic_sysclass = {
- .name = "lapic",
- .resume = lapic_resume,
- .suspend = lapic_suspend,
-};
+void __cpuinit setup_secondary_APIC_clock(void)
+{
+ check_boot_apic_timer_broadcast();
+ setup_APIC_timer();
+}
-static struct sys_device device_lapic = {
- .id = 0,
- .cls = &lapic_sysclass,
-};
+int setup_profiling_timer(unsigned int multiplier)
+{
+ return -EINVAL;
+}
-static void __cpuinit apic_pm_activate(void)
+void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
+ unsigned char msg_type, unsigned char mask)
{
- apic_pm_state.active = 1;
+ unsigned long reg = (lvt_off << 4) + K8_APIC_EXT_LVT_BASE;
+ unsigned int v = (mask << 16) | (msg_type << 8) | vector;
+ apic_write(reg, v);
}
-static int __init init_lapic_sysfs(void)
+/*
+ * Local timer interrupt handler. It does both profiling and
+ * process statistics/rescheduling.
+ *
+ * We do profiling in every local tick, statistics/rescheduling
+ * happen only every 'profiling multiplier' ticks. The default
+ * multiplier is 1 and it can be changed by writing the new multiplier
+ * value into /proc/profile.
+ */
+
+void smp_local_timer_interrupt(void)
{
- int error;
+ int cpu = smp_processor_id();
+ struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
- if (!cpu_has_apic)
- return 0;
- /* XXX: remove suspend/resume procs if !apic_pm_state.active? */
+ /*
+ * Normally we should not be here till LAPIC has been initialized but
+ * in some cases like kdump, its possible that there is a pending LAPIC
+ * timer interrupt from previous kernel's context and is delivered in
+ * new kernel the moment interrupts are enabled.
+ *
+ * Interrupts are enabled early and LAPIC is setup much later, hence
+ * its possible that when we get here evt->event_handler is NULL.
+ * Check for event_handler being NULL and discard the interrupt as
+ * spurious.
+ */
+ if (!evt->event_handler) {
+ printk(KERN_WARNING
+ "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
+ /* Switch it off */
+ lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+ return;
+ }
- error = sysdev_class_register(&lapic_sysclass);
- if (!error)
- error = sysdev_register(&device_lapic);
- return error;
-}
-device_initcall(init_lapic_sysfs);
+ /*
+ * the NMI deadlock-detector uses this.
+ */
+ add_pda(apic_timer_irqs, 1);
-#else /* CONFIG_PM */
+ evt->event_handler(evt);
+}
-static void apic_pm_activate(void) { }
+/*
+ * Local APIC timer interrupt. This is the most natural way for doing
+ * local interrupts, but local timer interrupts can be emulated by
+ * broadcast interrupts too. [in case the hw doesn't support APIC timers]
+ *
+ * [ if a single-CPU system runs an SMP kernel then we call the local
+ * interrupt as well. Thus we cannot inline the local irq ... ]
+ */
+void smp_apic_timer_interrupt(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
-#endif /* CONFIG_PM */
+ /*
+ * NOTE! We'd better ACK the irq immediately,
+ * because timer handling can be slow.
+ */
+ ack_APIC_irq();
+ /*
+ * update_process_times() expects us to have done irq_enter().
+ * Besides, if we don't timer interrupts ignore the global
+ * interrupt lock, which is the WrongThing (tm) to do.
+ */
+ exit_idle();
+ irq_enter();
+ smp_local_timer_interrupt();
+ irq_exit();
+ set_irq_regs(old_regs);
+}
/*
* apic_is_clustered_box() -- Check if we can expect good TSC
@@ -1180,34 +1103,21 @@ __cpuinit int apic_is_clustered_box(void)
{
int i, clusters, zeros;
unsigned id;
- u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
for (i = 0; i < NR_CPUS; i++) {
- /* are we being called early in kernel startup? */
- if (bios_cpu_apicid) {
- id = bios_cpu_apicid[i];
- }
- else if (i < nr_cpu_ids) {
- if (cpu_present(i))
- id = per_cpu(x86_bios_cpu_apicid, i);
- else
- continue;
- }
- else
- break;
-
+ id = bios_cpu_apicid[i];
if (id != BAD_APICID)
__set_bit(APIC_CLUSTERID(id), clustermap);
}
/* Problem: Partially populated chassis may not have CPUs in some of
* the APIC clusters they have been allocated. Only present CPUs have
- * x86_bios_cpu_apicid entries, thus causing zeroes in the bitmap.
- * Since clusters are allocated sequentially, count zeros only if
- * they are bounded by ones.
+ * bios_cpu_apicid entries, thus causing zeroes in the bitmap. Since
+ * clusters are allocated sequentially, count zeros only if they are
+ * bounded by ones.
*/
clusters = 0;
zeros = 0;
@@ -1228,33 +1138,96 @@ __cpuinit int apic_is_clustered_box(void)
}
/*
- * APIC command line parameters
+ * This interrupt should _never_ happen with our APIC/SMP architecture
*/
-static int __init apic_set_verbosity(char *str)
+asmlinkage void smp_spurious_interrupt(void)
{
- if (str == NULL) {
- skip_ioapic_setup = 0;
- ioapic_force = 1;
- return 0;
+ unsigned int v;
+ exit_idle();
+ irq_enter();
+ /*
+ * Check if this really is a spurious interrupt and ACK it
+ * if it is a vectored one. Just in case...
+ * Spurious interrupts should not be ACKed.
+ */
+ v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
+ if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
+ ack_APIC_irq();
+
+ add_pda(irq_spurious_count, 1);
+ irq_exit();
+}
+
+/*
+ * This interrupt should never happen with our APIC/SMP architecture
+ */
+
+asmlinkage void smp_error_interrupt(void)
+{
+ unsigned int v, v1;
+
+ exit_idle();
+ irq_enter();
+ /* First tickle the hardware, only then report what went on. -- REW */
+ v = apic_read(APIC_ESR);
+ apic_write(APIC_ESR, 0);
+ v1 = apic_read(APIC_ESR);
+ ack_APIC_irq();
+ atomic_inc(&irq_err_count);
+
+ /* Here is what the APIC error bits mean:
+ 0: Send CS error
+ 1: Receive CS error
+ 2: Send accept error
+ 3: Receive accept error
+ 4: Reserved
+ 5: Send illegal vector
+ 6: Received illegal vector
+ 7: Illegal register address
+ */
+ printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
+ smp_processor_id(), v , v1);
+ irq_exit();
+}
+
+int disable_apic;
+
+/*
+ * This initializes the IO-APIC and APIC hardware if this is
+ * a UP kernel.
+ */
+int __init APIC_init_uniprocessor (void)
+{
+ if (disable_apic) {
+ printk(KERN_INFO "Apic disabled\n");
+ return -1;
}
- if (strcmp("debug", str) == 0)
- apic_verbosity = APIC_DEBUG;
- else if (strcmp("verbose", str) == 0)
- apic_verbosity = APIC_VERBOSE;
- else {
- printk(KERN_WARNING "APIC Verbosity level %s not recognised"
- " use apic=verbose or apic=debug\n", str);
- return -EINVAL;
+ if (!cpu_has_apic) {
+ disable_apic = 1;
+ printk(KERN_INFO "Apic disabled by BIOS\n");
+ return -1;
}
+ verify_local_APIC();
+
+ phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
+ apic_write(APIC_ID, SET_APIC_ID(boot_cpu_id));
+
+ setup_local_APIC();
+
+ if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
+ setup_IO_APIC();
+ else
+ nr_ioapics = 0;
+ setup_boot_APIC_clock();
+ check_nmi_watchdog();
return 0;
}
-early_param("apic", apic_set_verbosity);
static __init int setup_disableapic(char *str)
{
disable_apic = 1;
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+ clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
return 0;
}
early_param("disableapic", setup_disableapic);
diff --git a/trunk/arch/x86/kernel/apm_32.c b/trunk/arch/x86/kernel/apm_32.c
index d4438ef296d8..af045ca0f653 100644
--- a/trunk/arch/x86/kernel/apm_32.c
+++ b/trunk/arch/x86/kernel/apm_32.c
@@ -227,7 +227,6 @@
#include
#include
#include
-#include
#include
#include
@@ -236,6 +235,8 @@
#include
#include
+#include "io_ports.h"
+
#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
extern int (*console_blank_hook)(int);
#endif
@@ -323,7 +324,7 @@ extern int (*console_blank_hook)(int);
/*
* Ignore suspend events for this amount of time after a resume
*/
-#define DEFAULT_BOUNCE_INTERVAL (3 * HZ)
+#define DEFAULT_BOUNCE_INTERVAL (3 * HZ)
/*
* Maximum number of events stored
@@ -335,7 +336,7 @@ extern int (*console_blank_hook)(int);
*/
struct apm_user {
int magic;
- struct apm_user *next;
+ struct apm_user * next;
unsigned int suser: 1;
unsigned int writer: 1;
unsigned int reader: 1;
@@ -371,44 +372,44 @@ struct apm_user {
static struct {
unsigned long offset;
unsigned short segment;
-} apm_bios_entry;
-static int clock_slowed;
-static int idle_threshold __read_mostly = DEFAULT_IDLE_THRESHOLD;
-static int idle_period __read_mostly = DEFAULT_IDLE_PERIOD;
-static int set_pm_idle;
-static int suspends_pending;
-static int standbys_pending;
-static int ignore_sys_suspend;
-static int ignore_normal_resume;
-static int bounce_interval __read_mostly = DEFAULT_BOUNCE_INTERVAL;
-
-static int debug __read_mostly;
-static int smp __read_mostly;
-static int apm_disabled = -1;
+} apm_bios_entry;
+static int clock_slowed;
+static int idle_threshold __read_mostly = DEFAULT_IDLE_THRESHOLD;
+static int idle_period __read_mostly = DEFAULT_IDLE_PERIOD;
+static int set_pm_idle;
+static int suspends_pending;
+static int standbys_pending;
+static int ignore_sys_suspend;
+static int ignore_normal_resume;
+static int bounce_interval __read_mostly = DEFAULT_BOUNCE_INTERVAL;
+
+static int debug __read_mostly;
+static int smp __read_mostly;
+static int apm_disabled = -1;
#ifdef CONFIG_SMP
-static int power_off;
+static int power_off;
#else
-static int power_off = 1;
+static int power_off = 1;
#endif
#ifdef CONFIG_APM_REAL_MODE_POWER_OFF
-static int realmode_power_off = 1;
+static int realmode_power_off = 1;
#else
-static int realmode_power_off;
+static int realmode_power_off;
#endif
#ifdef CONFIG_APM_ALLOW_INTS
-static int allow_ints = 1;
+static int allow_ints = 1;
#else
-static int allow_ints;
+static int allow_ints;
#endif
-static int broken_psr;
+static int broken_psr;
static DECLARE_WAIT_QUEUE_HEAD(apm_waitqueue);
static DECLARE_WAIT_QUEUE_HEAD(apm_suspend_waitqueue);
-static struct apm_user *user_list;
+static struct apm_user * user_list;
static DEFINE_SPINLOCK(user_list_lock);
-static const struct desc_struct bad_bios_desc = { { { 0, 0x00409200 } } };
+static const struct desc_struct bad_bios_desc = { 0, 0x00409200 };
-static const char driver_version[] = "1.16ac"; /* no spaces */
+static const char driver_version[] = "1.16ac"; /* no spaces */
static struct task_struct *kapmd_task;
@@ -416,7 +417,7 @@ static struct task_struct *kapmd_task;
* APM event names taken from the APM 1.2 specification. These are
* the message codes that the BIOS uses to tell us about events
*/
-static const char * const apm_event_name[] = {
+static const char * const apm_event_name[] = {
"system standby",
"system suspend",
"normal resume",
@@ -434,14 +435,14 @@ static const char * const apm_event_name[] = {
typedef struct lookup_t {
int key;
- char *msg;
+ char * msg;
} lookup_t;
/*
* The BIOS returns a set of standard error codes in AX when the
* carry flag is set.
*/
-
+
static const lookup_t error_table[] = {
/* N/A { APM_SUCCESS, "Operation succeeded" }, */
{ APM_DISABLED, "Power management disabled" },
@@ -471,25 +472,24 @@ static const lookup_t error_table[] = {
* Write a meaningful log entry to the kernel log in the event of
* an APM error.
*/
-
+
static void apm_error(char *str, int err)
{
- int i;
+ int i;
for (i = 0; i < ERROR_COUNT; i++)
- if (error_table[i].key == err)
- break;
+ if (error_table[i].key == err) break;
if (i < ERROR_COUNT)
printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg);
else
printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n",
- str, err);
+ str, err);
}
/*
* Lock APM functionality to physical CPU 0
*/
-
+
#ifdef CONFIG_SMP
static cpumask_t apm_save_cpus(void)
@@ -511,7 +511,7 @@ static inline void apm_restore_cpus(cpumask_t mask)
/*
* No CPU lockdown needed on a uniprocessor
*/
-
+
#define apm_save_cpus() (current->cpus_allowed)
#define apm_restore_cpus(x) (void)(x)
@@ -590,7 +590,7 @@ static inline void apm_irq_restore(unsigned long flags)
* code is returned in AH (bits 8-15 of eax) and this function
* returns non-zero.
*/
-
+
static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi)
{
@@ -602,7 +602,7 @@ static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
struct desc_struct *gdt;
cpus = apm_save_cpus();
-
+
cpu = get_cpu();
gdt = get_cpu_gdt_table(cpu);
save_desc_40 = gdt[0x40 / 8];
@@ -616,7 +616,7 @@ static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
gdt[0x40 / 8] = save_desc_40;
put_cpu();
apm_restore_cpus(cpus);
-
+
return *eax & 0xff;
}
@@ -645,7 +645,7 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
struct desc_struct *gdt;
cpus = apm_save_cpus();
-
+
cpu = get_cpu();
gdt = get_cpu_gdt_table(cpu);
save_desc_40 = gdt[0x40 / 8];
@@ -680,7 +680,7 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
static int apm_driver_version(u_short *val)
{
- u32 eax;
+ u32 eax;
if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax))
return (eax >> 8) & 0xff;
@@ -704,16 +704,16 @@ static int apm_driver_version(u_short *val)
* that APM 1.2 is in use. If no messges are pending the value 0x80
* is returned (No power management events pending).
*/
-
+
static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
{
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 dummy;
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 dummy;
if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx,
- &dummy, &dummy))
+ &dummy, &dummy))
return (eax >> 8) & 0xff;
*event = ebx;
if (apm_info.connection_version < 0x0102)
@@ -736,10 +736,10 @@ static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
* The state holds the state to transition to, which may in fact
* be an acceptance of a BIOS requested state change.
*/
-
+
static int set_power_state(u_short what, u_short state)
{
- u32 eax;
+ u32 eax;
if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax))
return (eax >> 8) & 0xff;
@@ -752,7 +752,7 @@ static int set_power_state(u_short what, u_short state)
*
* Transition the entire system into a new APM power state.
*/
-
+
static int set_system_power_state(u_short state)
{
return set_power_state(APM_DEVICE_ALL, state);
@@ -766,13 +766,13 @@ static int set_system_power_state(u_short state)
* to handle the idle request. On a success the function returns 1
* if the BIOS did clock slowing or 0 otherwise.
*/
-
+
static int apm_do_idle(void)
{
- u32 eax;
- u8 ret = 0;
- int idled = 0;
- int polling;
+ u32 eax;
+ u8 ret = 0;
+ int idled = 0;
+ int polling;
polling = !!(current_thread_info()->status & TS_POLLING);
if (polling) {
@@ -799,9 +799,10 @@ static int apm_do_idle(void)
/* This always fails on some SMP boards running UP kernels.
* Only report the failure the first 5 times.
*/
- if (++t < 5) {
+ if (++t < 5)
+ {
printk(KERN_DEBUG "apm_do_idle failed (%d)\n",
- (eax >> 8) & 0xff);
+ (eax >> 8) & 0xff);
t = jiffies;
}
return -1;
@@ -813,15 +814,15 @@ static int apm_do_idle(void)
/**
* apm_do_busy - inform the BIOS the CPU is busy
*
- * Request that the BIOS brings the CPU back to full performance.
+ * Request that the BIOS brings the CPU back to full performance.
*/
-
+
static void apm_do_busy(void)
{
- u32 dummy;
+ u32 dummy;
if (clock_slowed || ALWAYS_CALL_BUSY) {
- (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy);
+ (void) apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy);
clock_slowed = 0;
}
}
@@ -832,15 +833,15 @@ static void apm_do_busy(void)
* power management - we probably want
* to conserve power.
*/
-#define IDLE_CALC_LIMIT (HZ * 100)
-#define IDLE_LEAKY_MAX 16
+#define IDLE_CALC_LIMIT (HZ * 100)
+#define IDLE_LEAKY_MAX 16
static void (*original_pm_idle)(void) __read_mostly;
/**
* apm_cpu_idle - cpu idling for APM capable Linux
*
- * This is the idling function the kernel executes when APM is available. It
+ * This is the idling function the kernel executes when APM is available. It
* tries to do BIOS powermanagement based on the average system idle time.
* Furthermore it calls the system default idle routine.
*/
@@ -881,8 +882,7 @@ static void apm_cpu_idle(void)
t = jiffies;
switch (apm_do_idle()) {
- case 0:
- apm_idle_done = 1;
+ case 0: apm_idle_done = 1;
if (t != jiffies) {
if (bucket) {
bucket = IDLE_LEAKY_MAX;
@@ -893,8 +893,7 @@ static void apm_cpu_idle(void)
continue;
}
break;
- case 1:
- apm_idle_done = 1;
+ case 1: apm_idle_done = 1;
break;
default: /* BIOS refused */
break;
@@ -922,10 +921,10 @@ static void apm_cpu_idle(void)
* the SMP call on CPU0 as some systems will only honour this call
* on their first cpu.
*/
-
+
static void apm_power_off(void)
{
- unsigned char po_bios_call[] = {
+ unsigned char po_bios_call[] = {
0xb8, 0x00, 0x10, /* movw $0x1000,ax */
0x8e, 0xd0, /* movw ax,ss */
0xbc, 0x00, 0xf0, /* movw $0xf000,sp */
@@ -936,12 +935,13 @@ static void apm_power_off(void)
};
/* Some bioses don't like being called from CPU != 0 */
- if (apm_info.realmode_power_off) {
+ if (apm_info.realmode_power_off)
+ {
(void)apm_save_cpus();
machine_real_restart(po_bios_call, sizeof(po_bios_call));
- } else {
- (void)set_system_power_state(APM_STATE_OFF);
}
+ else
+ (void) set_system_power_state(APM_STATE_OFF);
}
#ifdef CONFIG_APM_DO_ENABLE
@@ -950,17 +950,17 @@ static void apm_power_off(void)
* apm_enable_power_management - enable BIOS APM power management
* @enable: enable yes/no
*
- * Enable or disable the APM BIOS power services.
+ * Enable or disable the APM BIOS power services.
*/
-
+
static int apm_enable_power_management(int enable)
{
- u32 eax;
+ u32 eax;
if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED))
return APM_NOT_ENGAGED;
if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL,
- enable, &eax))
+ enable, &eax))
return (eax >> 8) & 0xff;
if (enable)
apm_info.bios.flags &= ~APM_BIOS_DISABLED;
@@ -983,19 +983,19 @@ static int apm_enable_power_management(int enable)
* if reported is a lifetime in secodnds/minutes at current powwer
* consumption.
*/
-
+
static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
{
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 edx;
- u32 dummy;
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+ u32 dummy;
if (apm_info.get_power_status_broken)
return APM_32_UNSUPPORTED;
if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0,
- &eax, &ebx, &ecx, &edx, &dummy))
+ &eax, &ebx, &ecx, &edx, &dummy))
return (eax >> 8) & 0xff;
*status = ebx;
*bat = ecx;
@@ -1011,11 +1011,11 @@ static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
static int apm_get_battery_status(u_short which, u_short *status,
u_short *bat, u_short *life, u_short *nbat)
{
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 edx;
- u32 esi;
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+ u32 esi;
if (apm_info.connection_version < 0x0102) {
/* pretend we only have one battery. */
@@ -1026,7 +1026,7 @@ static int apm_get_battery_status(u_short which, u_short *status,
}
if (apm_bios_call(APM_FUNC_GET_STATUS, (0x8000 | (which)), 0, &eax,
- &ebx, &ecx, &edx, &esi))
+ &ebx, &ecx, &edx, &esi))
return (eax >> 8) & 0xff;
*status = ebx;
*bat = ecx;
@@ -1044,10 +1044,10 @@ static int apm_get_battery_status(u_short which, u_short *status,
* Activate or deactive power management on either a specific device
* or the entire system (%APM_DEVICE_ALL).
*/
-
+
static int apm_engage_power_management(u_short device, int enable)
{
- u32 eax;
+ u32 eax;
if ((enable == 0) && (device == APM_DEVICE_ALL)
&& (apm_info.bios.flags & APM_BIOS_DISABLED))
@@ -1074,7 +1074,7 @@ static int apm_engage_power_management(u_short device, int enable)
* all video devices. Typically the BIOS will do laptop backlight and
* monitor powerdown for us.
*/
-
+
static int apm_console_blank(int blank)
{
int error = APM_NOT_ENGAGED; /* silence gcc */
@@ -1126,7 +1126,7 @@ static apm_event_t get_queued_event(struct apm_user *as)
static void queue_event(apm_event_t event, struct apm_user *sender)
{
- struct apm_user *as;
+ struct apm_user * as;
spin_lock(&user_list_lock);
if (user_list == NULL)
@@ -1174,11 +1174,11 @@ static void reinit_timer(void)
spin_lock_irqsave(&i8253_lock, flags);
/* set the clock to HZ */
- outb_pit(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */
+ outb_p(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */
udelay(10);
- outb_pit(LATCH & 0xff, PIT_CH0); /* LSB */
+ outb_p(LATCH & 0xff, PIT_CH0); /* LSB */
udelay(10);
- outb_pit(LATCH >> 8, PIT_CH0); /* MSB */
+ outb(LATCH >> 8, PIT_CH0); /* MSB */
udelay(10);
spin_unlock_irqrestore(&i8253_lock, flags);
#endif
@@ -1186,7 +1186,7 @@ static void reinit_timer(void)
static int suspend(int vetoable)
{
- int err;
+ int err;
struct apm_user *as;
if (pm_send_all(PM_SUSPEND, (void *)3)) {
@@ -1239,7 +1239,7 @@ static int suspend(int vetoable)
static void standby(void)
{
- int err;
+ int err;
local_irq_disable();
device_power_down(PMSG_SUSPEND);
@@ -1256,8 +1256,8 @@ static void standby(void)
static apm_event_t get_event(void)
{
- int error;
- apm_event_t event = APM_NO_EVENTS; /* silence gcc */
+ int error;
+ apm_event_t event = APM_NO_EVENTS; /* silence gcc */
apm_eventinfo_t info;
static int notified;
@@ -1275,9 +1275,9 @@ static apm_event_t get_event(void)
static void check_events(void)
{
- apm_event_t event;
- static unsigned long last_resume;
- static int ignore_bounce;
+ apm_event_t event;
+ static unsigned long last_resume;
+ static int ignore_bounce;
while ((event = get_event()) != 0) {
if (debug) {
@@ -1289,7 +1289,7 @@ static void check_events(void)
"event 0x%02x\n", event);
}
if (ignore_bounce
- && (time_after(jiffies, last_resume + bounce_interval)))
+ && ((jiffies - last_resume) > bounce_interval))
ignore_bounce = 0;
switch (event) {
@@ -1357,7 +1357,7 @@ static void check_events(void)
/*
* We are not allowed to reject a critical suspend.
*/
- (void)suspend(0);
+ (void) suspend(0);
break;
}
}
@@ -1365,12 +1365,12 @@ static void check_events(void)
static void apm_event_handler(void)
{
- static int pending_count = 4;
- int err;
+ static int pending_count = 4;
+ int err;
if ((standbys_pending > 0) || (suspends_pending > 0)) {
if ((apm_info.connection_version > 0x100) &&
- (pending_count-- <= 0)) {
+ (pending_count-- <= 0)) {
pending_count = 4;
if (debug)
printk(KERN_DEBUG "apm: setting state busy\n");
@@ -1418,9 +1418,9 @@ static int check_apm_user(struct apm_user *as, const char *func)
static ssize_t do_read(struct file *fp, char __user *buf, size_t count, loff_t *ppos)
{
- struct apm_user *as;
- int i;
- apm_event_t event;
+ struct apm_user * as;
+ int i;
+ apm_event_t event;
as = fp->private_data;
if (check_apm_user(as, "read"))
@@ -1459,9 +1459,9 @@ static ssize_t do_read(struct file *fp, char __user *buf, size_t count, loff_t *
return 0;
}
-static unsigned int do_poll(struct file *fp, poll_table *wait)
+static unsigned int do_poll(struct file *fp, poll_table * wait)
{
- struct apm_user *as;
+ struct apm_user * as;
as = fp->private_data;
if (check_apm_user(as, "poll"))
@@ -1472,10 +1472,10 @@ static unsigned int do_poll(struct file *fp, poll_table *wait)
return 0;
}
-static int do_ioctl(struct inode *inode, struct file *filp,
+static int do_ioctl(struct inode * inode, struct file *filp,
u_int cmd, u_long arg)
{
- struct apm_user *as;
+ struct apm_user * as;
as = filp->private_data;
if (check_apm_user(as, "ioctl"))
@@ -1515,9 +1515,9 @@ static int do_ioctl(struct inode *inode, struct file *filp,
return 0;
}
-static int do_release(struct inode *inode, struct file *filp)
+static int do_release(struct inode * inode, struct file * filp)
{
- struct apm_user *as;
+ struct apm_user * as;
as = filp->private_data;
if (check_apm_user(as, "release"))
@@ -1533,11 +1533,11 @@ static int do_release(struct inode *inode, struct file *filp)
if (suspends_pending <= 0)
(void) suspend(1);
}
- spin_lock(&user_list_lock);
+ spin_lock(&user_list_lock);
if (user_list == as)
user_list = as->next;
else {
- struct apm_user *as1;
+ struct apm_user * as1;
for (as1 = user_list;
(as1 != NULL) && (as1->next != as);
@@ -1553,9 +1553,9 @@ static int do_release(struct inode *inode, struct file *filp)
return 0;
}
-static int do_open(struct inode *inode, struct file *filp)
+static int do_open(struct inode * inode, struct file * filp)
{
- struct apm_user *as;
+ struct apm_user * as;
as = kmalloc(sizeof(*as), GFP_KERNEL);
if (as == NULL) {
@@ -1569,7 +1569,7 @@ static int do_open(struct inode *inode, struct file *filp)
as->suspends_read = as->standbys_read = 0;
/*
* XXX - this is a tiny bit broken, when we consider BSD
- * process accounting. If the device is opened by root, we
+ * process accounting. If the device is opened by root, we
* instantly flag that we used superuser privs. Who knows,
* we might close the device immediately without doing a
* privileged operation -- cevans
@@ -1652,16 +1652,16 @@ static int proc_apm_show(struct seq_file *m, void *v)
8) min = minutes; sec = seconds */
seq_printf(m, "%s %d.%d 0x%02x 0x%02x 0x%02x 0x%02x %d%% %d %s\n",
- driver_version,
- (apm_info.bios.version >> 8) & 0xff,
- apm_info.bios.version & 0xff,
- apm_info.bios.flags,
- ac_line_status,
- battery_status,
- battery_flag,
- percentage,
- time_units,
- units);
+ driver_version,
+ (apm_info.bios.version >> 8) & 0xff,
+ apm_info.bios.version & 0xff,
+ apm_info.bios.flags,
+ ac_line_status,
+ battery_status,
+ battery_flag,
+ percentage,
+ time_units,
+ units);
return 0;
}
@@ -1684,8 +1684,8 @@ static int apm(void *unused)
unsigned short cx;
unsigned short dx;
int error;
- char *power_stat;
- char *bat_stat;
+ char * power_stat;
+ char * bat_stat;
#ifdef CONFIG_SMP
/* 2002/08/01 - WT
@@ -1744,41 +1744,23 @@ static int apm(void *unused)
}
}
- if (debug && (num_online_cpus() == 1 || smp)) {
+ if (debug && (num_online_cpus() == 1 || smp )) {
error = apm_get_power_status(&bx, &cx, &dx);
if (error)
printk(KERN_INFO "apm: power status not available\n");
else {
switch ((bx >> 8) & 0xff) {
- case 0:
- power_stat = "off line";
- break;
- case 1:
- power_stat = "on line";
- break;
- case 2:
- power_stat = "on backup power";
- break;
- default:
- power_stat = "unknown";
- break;
+ case 0: power_stat = "off line"; break;
+ case 1: power_stat = "on line"; break;
+ case 2: power_stat = "on backup power"; break;
+ default: power_stat = "unknown"; break;
}
switch (bx & 0xff) {
- case 0:
- bat_stat = "high";
- break;
- case 1:
- bat_stat = "low";
- break;
- case 2:
- bat_stat = "critical";
- break;
- case 3:
- bat_stat = "charging";
- break;
- default:
- bat_stat = "unknown";
- break;
+ case 0: bat_stat = "high"; break;
+ case 1: bat_stat = "low"; break;
+ case 2: bat_stat = "critical"; break;
+ case 3: bat_stat = "charging"; break;
+ default: bat_stat = "unknown"; break;
}
printk(KERN_INFO
"apm: AC %s, battery status %s, battery life ",
@@ -1795,8 +1777,8 @@ static int apm(void *unused)
printk("unknown\n");
else
printk("%d %s\n", dx & 0x7fff,
- (dx & 0x8000) ?
- "minutes" : "seconds");
+ (dx & 0x8000) ?
+ "minutes" : "seconds");
}
}
}
@@ -1821,7 +1803,7 @@ static int apm(void *unused)
#ifndef MODULE
static int __init apm_setup(char *str)
{
- int invert;
+ int invert;
while ((str != NULL) && (*str != '\0')) {
if (strncmp(str, "off", 3) == 0)
@@ -1846,13 +1828,14 @@ static int __init apm_setup(char *str)
if ((strncmp(str, "power-off", 9) == 0) ||
(strncmp(str, "power_off", 9) == 0))
power_off = !invert;
- if (strncmp(str, "smp", 3) == 0) {
+ if (strncmp(str, "smp", 3) == 0)
+ {
smp = !invert;
idle_threshold = 100;
}
if ((strncmp(str, "allow-ints", 10) == 0) ||
(strncmp(str, "allow_ints", 10) == 0))
- apm_info.allow_ints = !invert;
+ apm_info.allow_ints = !invert;
if ((strncmp(str, "broken-psr", 10) == 0) ||
(strncmp(str, "broken_psr", 10) == 0))
apm_info.get_power_status_broken = !invert;
@@ -1898,8 +1881,7 @@ static int __init print_if_true(const struct dmi_system_id *d)
*/
static int __init broken_ps2_resume(const struct dmi_system_id *d)
{
- printk(KERN_INFO "%s machine detected. Mousepad Resume Bug "
- "workaround hopefully not needed.\n", d->ident);
+ printk(KERN_INFO "%s machine detected. Mousepad Resume Bug workaround hopefully not needed.\n", d->ident);
return 0;
}
@@ -1908,8 +1890,7 @@ static int __init set_realmode_power_off(const struct dmi_system_id *d)
{
if (apm_info.realmode_power_off == 0) {
apm_info.realmode_power_off = 1;
- printk(KERN_INFO "%s bios detected. "
- "Using realmode poweroff only.\n", d->ident);
+ printk(KERN_INFO "%s bios detected. Using realmode poweroff only.\n", d->ident);
}
return 0;
}
@@ -1919,8 +1900,7 @@ static int __init set_apm_ints(const struct dmi_system_id *d)
{
if (apm_info.allow_ints == 0) {
apm_info.allow_ints = 1;
- printk(KERN_INFO "%s machine detected. "
- "Enabling interrupts during APM calls.\n", d->ident);
+ printk(KERN_INFO "%s machine detected. Enabling interrupts during APM calls.\n", d->ident);
}
return 0;
}
@@ -1930,8 +1910,7 @@ static int __init apm_is_horked(const struct dmi_system_id *d)
{
if (apm_info.disabled == 0) {
apm_info.disabled = 1;
- printk(KERN_INFO "%s machine detected. "
- "Disabling APM.\n", d->ident);
+ printk(KERN_INFO "%s machine detected. Disabling APM.\n", d->ident);
}
return 0;
}
@@ -1940,8 +1919,7 @@ static int __init apm_is_horked_d850md(const struct dmi_system_id *d)
{
if (apm_info.disabled == 0) {
apm_info.disabled = 1;
- printk(KERN_INFO "%s machine detected. "
- "Disabling APM.\n", d->ident);
+ printk(KERN_INFO "%s machine detected. Disabling APM.\n", d->ident);
printk(KERN_INFO "This bug is fixed in bios P15 which is available for \n");
printk(KERN_INFO "download from support.intel.com \n");
}
@@ -1953,8 +1931,7 @@ static int __init apm_likes_to_melt(const struct dmi_system_id *d)
{
if (apm_info.forbid_idle == 0) {
apm_info.forbid_idle = 1;
- printk(KERN_INFO "%s machine detected. "
- "Disabling APM idle calls.\n", d->ident);
+ printk(KERN_INFO "%s machine detected. Disabling APM idle calls.\n", d->ident);
}
return 0;
}
@@ -1977,8 +1954,7 @@ static int __init apm_likes_to_melt(const struct dmi_system_id *d)
static int __init broken_apm_power(const struct dmi_system_id *d)
{
apm_info.get_power_status_broken = 1;
- printk(KERN_WARNING "BIOS strings suggest APM bugs, "
- "disabling power status reporting.\n");
+ printk(KERN_WARNING "BIOS strings suggest APM bugs, disabling power status reporting.\n");
return 0;
}
@@ -1989,8 +1965,7 @@ static int __init broken_apm_power(const struct dmi_system_id *d)
static int __init swab_apm_power_in_minutes(const struct dmi_system_id *d)
{
apm_info.get_power_status_swabinminutes = 1;
- printk(KERN_WARNING "BIOS strings suggest APM reports battery life "
- "in minutes and wrong byte order.\n");
+ printk(KERN_WARNING "BIOS strings suggest APM reports battery life in minutes and wrong byte order.\n");
return 0;
}
@@ -2015,8 +1990,8 @@ static struct dmi_system_id __initdata apm_dmi_table[] = {
apm_is_horked, "Dell Inspiron 2500",
{ DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 2500"),
- DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "A11"), },
+ DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"),
+ DMI_MATCH(DMI_BIOS_VERSION,"A11"), },
},
{ /* Allow interrupts during suspend on Dell Inspiron laptops*/
set_apm_ints, "Dell Inspiron", {
@@ -2039,15 +2014,15 @@ static struct dmi_system_id __initdata apm_dmi_table[] = {
apm_is_horked, "Dell Dimension 4100",
{ DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
DMI_MATCH(DMI_PRODUCT_NAME, "XPS-Z"),
- DMI_MATCH(DMI_BIOS_VENDOR, "Intel Corp."),
- DMI_MATCH(DMI_BIOS_VERSION, "A11"), },
+ DMI_MATCH(DMI_BIOS_VENDOR,"Intel Corp."),
+ DMI_MATCH(DMI_BIOS_VERSION,"A11"), },
},
{ /* Allow interrupts during suspend on Compaq Laptops*/
set_apm_ints, "Compaq 12XL125",
{ DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
DMI_MATCH(DMI_PRODUCT_NAME, "Compaq PC"),
DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "4.06"), },
+ DMI_MATCH(DMI_BIOS_VERSION,"4.06"), },
},
{ /* Allow interrupts during APM or the clock goes slow */
set_apm_ints, "ASUSTeK",
@@ -2089,15 +2064,15 @@ static struct dmi_system_id __initdata apm_dmi_table[] = {
apm_is_horked, "Sharp PC-PJ/AX",
{ DMI_MATCH(DMI_SYS_VENDOR, "SHARP"),
DMI_MATCH(DMI_PRODUCT_NAME, "PC-PJ/AX"),
- DMI_MATCH(DMI_BIOS_VENDOR, "SystemSoft"),
- DMI_MATCH(DMI_BIOS_VERSION, "Version R2.08"), },
+ DMI_MATCH(DMI_BIOS_VENDOR,"SystemSoft"),
+ DMI_MATCH(DMI_BIOS_VERSION,"Version R2.08"), },
},
{ /* APM crashes */
apm_is_horked, "Dell Inspiron 2500",
{ DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 2500"),
- DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
- DMI_MATCH(DMI_BIOS_VERSION, "A11"), },
+ DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"),
+ DMI_MATCH(DMI_BIOS_VERSION,"A11"), },
},
{ /* APM idle hangs */
apm_likes_to_melt, "Jabil AMD",
@@ -2228,11 +2203,11 @@ static int __init apm_init(void)
return -ENODEV;
}
printk(KERN_INFO
- "apm: BIOS version %d.%d Flags 0x%02x (Driver version %s)\n",
- ((apm_info.bios.version >> 8) & 0xff),
- (apm_info.bios.version & 0xff),
- apm_info.bios.flags,
- driver_version);
+ "apm: BIOS version %d.%d Flags 0x%02x (Driver version %s)\n",
+ ((apm_info.bios.version >> 8) & 0xff),
+ (apm_info.bios.version & 0xff),
+ apm_info.bios.flags,
+ driver_version);
if ((apm_info.bios.flags & APM_32_BIT_SUPPORT) == 0) {
printk(KERN_INFO "apm: no 32 bit BIOS support\n");
return -ENODEV;
@@ -2337,9 +2312,9 @@ static int __init apm_init(void)
}
wake_up_process(kapmd_task);
- if (num_online_cpus() > 1 && !smp) {
+ if (num_online_cpus() > 1 && !smp ) {
printk(KERN_NOTICE
- "apm: disabled - APM is not SMP safe (power off active).\n");
+ "apm: disabled - APM is not SMP safe (power off active).\n");
return 0;
}
@@ -2364,7 +2339,7 @@ static int __init apm_init(void)
static void __exit apm_exit(void)
{
- int error;
+ int error;
if (set_pm_idle) {
pm_idle = original_pm_idle;
diff --git a/trunk/arch/x86/kernel/asm-offsets_32.c b/trunk/arch/x86/kernel/asm-offsets_32.c
index afd84463b712..0e45981b2dd7 100644
--- a/trunk/arch/x86/kernel/asm-offsets_32.c
+++ b/trunk/arch/x86/kernel/asm-offsets_32.c
@@ -38,15 +38,15 @@ void foo(void);
void foo(void)
{
- OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax);
- OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx);
- OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx);
- OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx);
- OFFSET(IA32_SIGCONTEXT_si, sigcontext, si);
- OFFSET(IA32_SIGCONTEXT_di, sigcontext, di);
- OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp);
- OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp);
- OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip);
+ OFFSET(SIGCONTEXT_eax, sigcontext, eax);
+ OFFSET(SIGCONTEXT_ebx, sigcontext, ebx);
+ OFFSET(SIGCONTEXT_ecx, sigcontext, ecx);
+ OFFSET(SIGCONTEXT_edx, sigcontext, edx);
+ OFFSET(SIGCONTEXT_esi, sigcontext, esi);
+ OFFSET(SIGCONTEXT_edi, sigcontext, edi);
+ OFFSET(SIGCONTEXT_ebp, sigcontext, ebp);
+ OFFSET(SIGCONTEXT_esp, sigcontext, esp);
+ OFFSET(SIGCONTEXT_eip, sigcontext, eip);
BLANK();
OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
@@ -70,38 +70,39 @@ void foo(void)
OFFSET(TI_cpu, thread_info, cpu);
BLANK();
- OFFSET(GDS_size, desc_ptr, size);
- OFFSET(GDS_address, desc_ptr, address);
+ OFFSET(GDS_size, Xgt_desc_struct, size);
+ OFFSET(GDS_address, Xgt_desc_struct, address);
+ OFFSET(GDS_pad, Xgt_desc_struct, pad);
BLANK();
- OFFSET(PT_EBX, pt_regs, bx);
- OFFSET(PT_ECX, pt_regs, cx);
- OFFSET(PT_EDX, pt_regs, dx);
- OFFSET(PT_ESI, pt_regs, si);
- OFFSET(PT_EDI, pt_regs, di);
- OFFSET(PT_EBP, pt_regs, bp);
- OFFSET(PT_EAX, pt_regs, ax);
- OFFSET(PT_DS, pt_regs, ds);
- OFFSET(PT_ES, pt_regs, es);
- OFFSET(PT_FS, pt_regs, fs);
- OFFSET(PT_ORIG_EAX, pt_regs, orig_ax);
- OFFSET(PT_EIP, pt_regs, ip);
- OFFSET(PT_CS, pt_regs, cs);
- OFFSET(PT_EFLAGS, pt_regs, flags);
- OFFSET(PT_OLDESP, pt_regs, sp);
- OFFSET(PT_OLDSS, pt_regs, ss);
+ OFFSET(PT_EBX, pt_regs, ebx);
+ OFFSET(PT_ECX, pt_regs, ecx);
+ OFFSET(PT_EDX, pt_regs, edx);
+ OFFSET(PT_ESI, pt_regs, esi);
+ OFFSET(PT_EDI, pt_regs, edi);
+ OFFSET(PT_EBP, pt_regs, ebp);
+ OFFSET(PT_EAX, pt_regs, eax);
+ OFFSET(PT_DS, pt_regs, xds);
+ OFFSET(PT_ES, pt_regs, xes);
+ OFFSET(PT_FS, pt_regs, xfs);
+ OFFSET(PT_ORIG_EAX, pt_regs, orig_eax);
+ OFFSET(PT_EIP, pt_regs, eip);
+ OFFSET(PT_CS, pt_regs, xcs);
+ OFFSET(PT_EFLAGS, pt_regs, eflags);
+ OFFSET(PT_OLDESP, pt_regs, esp);
+ OFFSET(PT_OLDSS, pt_regs, xss);
BLANK();
OFFSET(EXEC_DOMAIN_handler, exec_domain, handler);
- OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
+ OFFSET(RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
BLANK();
OFFSET(pbe_address, pbe, address);
OFFSET(pbe_orig_address, pbe, orig_address);
OFFSET(pbe_next, pbe, next);
- /* Offset from the sysenter stack to tss.sp0 */
- DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
+ /* Offset from the sysenter stack to tss.esp0 */
+ DEFINE(TSS_sysenter_esp0, offsetof(struct tss_struct, x86_tss.esp0) -
sizeof(struct tss_struct));
DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
@@ -110,6 +111,8 @@ void foo(void)
DEFINE(PTRS_PER_PMD, PTRS_PER_PMD);
DEFINE(PTRS_PER_PGD, PTRS_PER_PGD);
+ DEFINE(VDSO_PRELINK_asm, VDSO_PRELINK);
+
OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
#ifdef CONFIG_PARAVIRT
@@ -120,7 +123,7 @@ void foo(void)
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
- OFFSET(PV_CPU_irq_enable_syscall_ret, pv_cpu_ops, irq_enable_syscall_ret);
+ OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
#endif
diff --git a/trunk/arch/x86/kernel/asm-offsets_64.c b/trunk/arch/x86/kernel/asm-offsets_64.c
index 494e1e096ee6..d1b6ed98774e 100644
--- a/trunk/arch/x86/kernel/asm-offsets_64.c
+++ b/trunk/arch/x86/kernel/asm-offsets_64.c
@@ -38,6 +38,7 @@ int main(void)
#define ENTRY(entry) DEFINE(tsk_ ## entry, offsetof(struct task_struct, entry))
ENTRY(state);
ENTRY(flags);
+ ENTRY(thread);
ENTRY(pid);
BLANK();
#undef ENTRY
@@ -46,9 +47,6 @@ int main(void)
ENTRY(addr_limit);
ENTRY(preempt_count);
ENTRY(status);
-#ifdef CONFIG_IA32_EMULATION
- ENTRY(sysenter_return);
-#endif
BLANK();
#undef ENTRY
#define ENTRY(entry) DEFINE(pda_ ## entry, offsetof(struct x8664_pda, entry))
@@ -61,31 +59,17 @@ int main(void)
ENTRY(data_offset);
BLANK();
#undef ENTRY
-#ifdef CONFIG_PARAVIRT
- BLANK();
- OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
- OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
- OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
- OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
- OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
- OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
- OFFSET(PV_CPU_irq_enable_syscall_ret, pv_cpu_ops, irq_enable_syscall_ret);
- OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
- OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
-#endif
-
-
#ifdef CONFIG_IA32_EMULATION
#define ENTRY(entry) DEFINE(IA32_SIGCONTEXT_ ## entry, offsetof(struct sigcontext_ia32, entry))
- ENTRY(ax);
- ENTRY(bx);
- ENTRY(cx);
- ENTRY(dx);
- ENTRY(si);
- ENTRY(di);
- ENTRY(bp);
- ENTRY(sp);
- ENTRY(ip);
+ ENTRY(eax);
+ ENTRY(ebx);
+ ENTRY(ecx);
+ ENTRY(edx);
+ ENTRY(esi);
+ ENTRY(edi);
+ ENTRY(ebp);
+ ENTRY(esp);
+ ENTRY(eip);
BLANK();
#undef ENTRY
DEFINE(IA32_RT_SIGFRAME_sigcontext,
@@ -97,14 +81,14 @@ int main(void)
DEFINE(pbe_next, offsetof(struct pbe, next));
BLANK();
#define ENTRY(entry) DEFINE(pt_regs_ ## entry, offsetof(struct pt_regs, entry))
- ENTRY(bx);
- ENTRY(bx);
- ENTRY(cx);
- ENTRY(dx);
- ENTRY(sp);
- ENTRY(bp);
- ENTRY(si);
- ENTRY(di);
+ ENTRY(rbx);
+ ENTRY(rbx);
+ ENTRY(rcx);
+ ENTRY(rdx);
+ ENTRY(rsp);
+ ENTRY(rbp);
+ ENTRY(rsi);
+ ENTRY(rdi);
ENTRY(r8);
ENTRY(r9);
ENTRY(r10);
@@ -113,7 +97,7 @@ int main(void)
ENTRY(r13);
ENTRY(r14);
ENTRY(r15);
- ENTRY(flags);
+ ENTRY(eflags);
BLANK();
#undef ENTRY
#define ENTRY(entry) DEFINE(saved_context_ ## entry, offsetof(struct saved_context, entry))
@@ -124,7 +108,7 @@ int main(void)
ENTRY(cr8);
BLANK();
#undef ENTRY
- DEFINE(TSS_ist, offsetof(struct tss_struct, x86_tss.ist));
+ DEFINE(TSS_ist, offsetof(struct tss_struct, ist));
BLANK();
DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx));
BLANK();
diff --git a/trunk/arch/x86/kernel/bootflag.c b/trunk/arch/x86/kernel/bootflag.c
index 30f25a75fe28..0b9860530a6b 100644
--- a/trunk/arch/x86/kernel/bootflag.c
+++ b/trunk/arch/x86/kernel/bootflag.c
@@ -1,6 +1,8 @@
/*
* Implement 'Simple Boot Flag Specification 2.0'
*/
+
+
#include
#include
#include
@@ -12,38 +14,40 @@
#include
+
#define SBF_RESERVED (0x78)
#define SBF_PNPOS (1<<0)
#define SBF_BOOTING (1<<1)
#define SBF_DIAG (1<<2)
#define SBF_PARITY (1<<7)
+
int sbf_port __initdata = -1; /* set via acpi_boot_init() */
+
static int __init parity(u8 v)
{
int x = 0;
int i;
-
- for (i = 0; i < 8; i++) {
- x ^= (v & 1);
- v >>= 1;
+
+ for(i=0;i<8;i++)
+ {
+ x^=(v&1);
+ v>>=1;
}
-
return x;
}
static void __init sbf_write(u8 v)
{
unsigned long flags;
-
- if (sbf_port != -1) {
+ if(sbf_port != -1)
+ {
v &= ~SBF_PARITY;
- if (!parity(v))
- v |= SBF_PARITY;
+ if(!parity(v))
+ v|=SBF_PARITY;
- printk(KERN_INFO "Simple Boot Flag at 0x%x set to 0x%x\n",
- sbf_port, v);
+ printk(KERN_INFO "Simple Boot Flag at 0x%x set to 0x%x\n", sbf_port, v);
spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(v, sbf_port);
@@ -53,41 +57,33 @@ static void __init sbf_write(u8 v)
static u8 __init sbf_read(void)
{
- unsigned long flags;
u8 v;
-
- if (sbf_port == -1)
+ unsigned long flags;
+ if(sbf_port == -1)
return 0;
-
spin_lock_irqsave(&rtc_lock, flags);
v = CMOS_READ(sbf_port);
spin_unlock_irqrestore(&rtc_lock, flags);
-
return v;
}
static int __init sbf_value_valid(u8 v)
{
- if (v & SBF_RESERVED) /* Reserved bits */
+ if(v&SBF_RESERVED) /* Reserved bits */
return 0;
- if (!parity(v))
+ if(!parity(v))
return 0;
-
return 1;
}
static int __init sbf_init(void)
{
u8 v;
-
- if (sbf_port == -1)
+ if(sbf_port == -1)
return 0;
-
v = sbf_read();
- if (!sbf_value_valid(v)) {
- printk(KERN_WARNING "Simple Boot Flag value 0x%x read from "
- "CMOS RAM was invalid\n", v);
- }
+ if(!sbf_value_valid(v))
+ printk(KERN_WARNING "Simple Boot Flag value 0x%x read from CMOS RAM was invalid\n",v);
v &= ~SBF_RESERVED;
v &= ~SBF_BOOTING;
@@ -96,7 +92,7 @@ static int __init sbf_init(void)
v |= SBF_PNPOS;
#endif
sbf_write(v);
-
return 0;
}
+
module_init(sbf_init);
diff --git a/trunk/arch/x86/kernel/bugs_64.c b/trunk/arch/x86/kernel/bugs_64.c
index 8f520f93ffd4..9a189cef6404 100644
--- a/trunk/arch/x86/kernel/bugs_64.c
+++ b/trunk/arch/x86/kernel/bugs_64.c
@@ -13,6 +13,7 @@
void __init check_bugs(void)
{
identify_cpu(&boot_cpu_data);
+ mtrr_bp_init();
#if !defined(CONFIG_SMP)
printk("CPU: ");
print_cpu_info(&boot_cpu_data);
diff --git a/trunk/arch/x86/kernel/cpu/addon_cpuid_features.c b/trunk/arch/x86/kernel/cpu/addon_cpuid_features.c
index 238468ae1993..3e91d3ee26ec 100644
--- a/trunk/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/trunk/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -45,6 +45,6 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
®s[CR_ECX], ®s[CR_EDX]);
if (regs[cb->reg] & (1 << cb->bit))
- set_cpu_cap(c, cb->feature);
+ set_bit(cb->feature, c->x86_capability);
}
}
diff --git a/trunk/arch/x86/kernel/cpu/amd.c b/trunk/arch/x86/kernel/cpu/amd.c
index 06fa159232fd..1ff88c7f45cf 100644
--- a/trunk/arch/x86/kernel/cpu/amd.c
+++ b/trunk/arch/x86/kernel/cpu/amd.c
@@ -63,15 +63,6 @@ static __cpuinit int amd_apic_timer_broken(void)
int force_mwait __cpuinitdata;
-void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
-{
- if (cpuid_eax(0x80000000) >= 0x80000007) {
- c->x86_power = cpuid_edx(0x80000007);
- if (c->x86_power & (1<<8))
- set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
- }
-}
-
static void __cpuinit init_amd(struct cpuinfo_x86 *c)
{
u32 l, h;
@@ -94,8 +85,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
#endif
- early_init_amd(c);
-
/*
* FIXME: We should handle the K5 here. Set up the write
* range and also turn on MSR 83 bits 4 and 31 (write alloc,
@@ -268,6 +257,12 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
}
+ if (cpuid_eax(0x80000000) >= 0x80000007) {
+ c->x86_power = cpuid_edx(0x80000007);
+ if (c->x86_power & (1<<8))
+ set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
+ }
+
#ifdef CONFIG_X86_HT
/*
* On a AMD multi core setup the lower bits of the APIC id
@@ -300,12 +295,12 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
local_apic_timer_disabled = 1;
#endif
+ if (c->x86 == 0x10 && !force_mwait)
+ clear_bit(X86_FEATURE_MWAIT, c->x86_capability);
+
/* K6s reports MCEs but don't actually have all the MSRs */
if (c->x86 < 6)
clear_bit(X86_FEATURE_MCE, c->x86_capability);
-
- if (cpu_has_xmm)
- set_bit(X86_FEATURE_MFENCE_RDTSC, c->x86_capability);
}
static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 * c, unsigned int size)
diff --git a/trunk/arch/x86/kernel/cpu/bugs.c b/trunk/arch/x86/kernel/cpu/bugs.c
index 9b95edcfc6ae..205fd5ba57f7 100644
--- a/trunk/arch/x86/kernel/cpu/bugs.c
+++ b/trunk/arch/x86/kernel/cpu/bugs.c
@@ -11,7 +11,6 @@
#include
#include
#include
-#include
#include
#include
#include
@@ -36,7 +35,7 @@ __setup("mca-pentium", mca_pentium);
static int __init no_387(char *s)
{
boot_cpu_data.hard_math = 0;
- write_cr0(X86_CR0_TS | X86_CR0_EM | X86_CR0_MP | read_cr0());
+ write_cr0(0xE | read_cr0());
return 1;
}
@@ -154,7 +153,7 @@ static void __init check_config(void)
* If we configured ourselves for a TSC, we'd better have one!
*/
#ifdef CONFIG_X86_TSC
- if (!cpu_has_tsc)
+ if (!cpu_has_tsc && !tsc_disable)
panic("Kernel compiled for Pentium+, requires TSC feature!");
#endif
diff --git a/trunk/arch/x86/kernel/cpu/common.c b/trunk/arch/x86/kernel/cpu/common.c
index db28aa9e2f69..e2fcf2051bdb 100644
--- a/trunk/arch/x86/kernel/cpu/common.c
+++ b/trunk/arch/x86/kernel/cpu/common.c
@@ -22,48 +22,43 @@
#include "cpu.h"
DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
- [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
- [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
- [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
- [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff200 } } },
+ [GDT_ENTRY_KERNEL_CS] = { 0x0000ffff, 0x00cf9a00 },
+ [GDT_ENTRY_KERNEL_DS] = { 0x0000ffff, 0x00cf9200 },
+ [GDT_ENTRY_DEFAULT_USER_CS] = { 0x0000ffff, 0x00cffa00 },
+ [GDT_ENTRY_DEFAULT_USER_DS] = { 0x0000ffff, 0x00cff200 },
/*
* Segments used for calling PnP BIOS have byte granularity.
* They code segments and data segments have fixed 64k limits,
* the transfer segment sizes are set at run time.
*/
- /* 32-bit code */
- [GDT_ENTRY_PNPBIOS_CS32] = { { { 0x0000ffff, 0x00409a00 } } },
- /* 16-bit code */
- [GDT_ENTRY_PNPBIOS_CS16] = { { { 0x0000ffff, 0x00009a00 } } },
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_DS] = { { { 0x0000ffff, 0x00009200 } } },
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_TS1] = { { { 0x00000000, 0x00009200 } } },
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_TS2] = { { { 0x00000000, 0x00009200 } } },
+ [GDT_ENTRY_PNPBIOS_CS32] = { 0x0000ffff, 0x00409a00 },/* 32-bit code */
+ [GDT_ENTRY_PNPBIOS_CS16] = { 0x0000ffff, 0x00009a00 },/* 16-bit code */
+ [GDT_ENTRY_PNPBIOS_DS] = { 0x0000ffff, 0x00009200 }, /* 16-bit data */
+ [GDT_ENTRY_PNPBIOS_TS1] = { 0x00000000, 0x00009200 },/* 16-bit data */
+ [GDT_ENTRY_PNPBIOS_TS2] = { 0x00000000, 0x00009200 },/* 16-bit data */
/*
* The APM segments have byte granularity and their bases
* are set at run time. All have 64k limits.
*/
- /* 32-bit code */
- [GDT_ENTRY_APMBIOS_BASE] = { { { 0x0000ffff, 0x00409a00 } } },
+ [GDT_ENTRY_APMBIOS_BASE] = { 0x0000ffff, 0x00409a00 },/* 32-bit code */
/* 16-bit code */
- [GDT_ENTRY_APMBIOS_BASE+1] = { { { 0x0000ffff, 0x00009a00 } } },
- /* data */
- [GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } },
+ [GDT_ENTRY_APMBIOS_BASE+1] = { 0x0000ffff, 0x00009a00 },
+ [GDT_ENTRY_APMBIOS_BASE+2] = { 0x0000ffff, 0x00409200 }, /* data */
- [GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
- [GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } },
+ [GDT_ENTRY_ESPFIX_SS] = { 0x00000000, 0x00c09200 },
+ [GDT_ENTRY_PERCPU] = { 0x00000000, 0x00000000 },
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
-
static int cachesize_override __cpuinitdata = -1;
+static int disable_x86_fxsr __cpuinitdata;
static int disable_x86_serial_nr __cpuinitdata = 1;
+static int disable_x86_sep __cpuinitdata;
struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {};
+extern int disable_pse;
+
static void __cpuinit default_init(struct cpuinfo_x86 * c)
{
/* Not much we can do here... */
@@ -212,8 +207,16 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early)
static int __init x86_fxsr_setup(char * s)
{
- setup_clear_cpu_cap(X86_FEATURE_FXSR);
- setup_clear_cpu_cap(X86_FEATURE_XMM);
+ /* Tell all the other CPUs to not use it... */
+ disable_x86_fxsr = 1;
+
+ /*
+ * ... and clear the bits early in the boot_cpu_data
+ * so that the bootup process doesn't try to do this
+ * either.
+ */
+ clear_bit(X86_FEATURE_FXSR, boot_cpu_data.x86_capability);
+ clear_bit(X86_FEATURE_XMM, boot_cpu_data.x86_capability);
return 1;
}
__setup("nofxsr", x86_fxsr_setup);
@@ -221,7 +224,7 @@ __setup("nofxsr", x86_fxsr_setup);
static int __init x86_sep_setup(char * s)
{
- setup_clear_cpu_cap(X86_FEATURE_SEP);
+ disable_x86_sep = 1;
return 1;
}
__setup("nosep", x86_sep_setup);
@@ -278,33 +281,6 @@ void __init cpu_detect(struct cpuinfo_x86 *c)
c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
}
}
-static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
-{
- u32 tfms, xlvl;
- int ebx;
-
- memset(&c->x86_capability, 0, sizeof c->x86_capability);
- if (have_cpuid_p()) {
- /* Intel-defined flags: level 0x00000001 */
- if (c->cpuid_level >= 0x00000001) {
- u32 capability, excap;
- cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
- c->x86_capability[0] = capability;
- c->x86_capability[4] = excap;
- }
-
- /* AMD-defined flags: level 0x80000001 */
- xlvl = cpuid_eax(0x80000000);
- if ((xlvl & 0xffff0000) == 0x80000000) {
- if (xlvl >= 0x80000001) {
- c->x86_capability[1] = cpuid_edx(0x80000001);
- c->x86_capability[6] = cpuid_ecx(0x80000001);
- }
- }
-
- }
-
-}
/* Do minimum CPU detection early.
Fields really needed: vendor, cpuid_level, family, model, mask, cache alignment.
@@ -324,17 +300,6 @@ static void __init early_cpu_detect(void)
cpu_detect(c);
get_cpu_vendor(c, 1);
-
- switch (c->x86_vendor) {
- case X86_VENDOR_AMD:
- early_init_amd(c);
- break;
- case X86_VENDOR_INTEL:
- early_init_intel(c);
- break;
- }
-
- early_get_cap(c);
}
static void __cpuinit generic_identify(struct cpuinfo_x86 * c)
@@ -392,6 +357,8 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 * c)
init_scattered_cpuid_features(c);
}
+ early_intel_workaround(c);
+
#ifdef CONFIG_X86_HT
c->phys_proc_id = (cpuid_ebx(1) >> 24) & 0xff;
#endif
@@ -425,7 +392,7 @@ __setup("serialnumber", x86_serial_nr_setup);
/*
* This does the hard work of actually picking apart the CPU stuff...
*/
-void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
+static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
{
int i;
@@ -451,9 +418,20 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
generic_identify(c);
- if (this_cpu->c_identify)
+ printk(KERN_DEBUG "CPU: After generic identify, caps:");
+ for (i = 0; i < NCAPINTS; i++)
+ printk(" %08lx", c->x86_capability[i]);
+ printk("\n");
+
+ if (this_cpu->c_identify) {
this_cpu->c_identify(c);
+ printk(KERN_DEBUG "CPU: After vendor identify, caps:");
+ for (i = 0; i < NCAPINTS; i++)
+ printk(" %08lx", c->x86_capability[i]);
+ printk("\n");
+ }
+
/*
* Vendor-specific initialization. In this section we
* canonicalize the feature flags, meaning if there are
@@ -475,6 +453,23 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
* we do "generic changes."
*/
+ /* TSC disabled? */
+ if ( tsc_disable )
+ clear_bit(X86_FEATURE_TSC, c->x86_capability);
+
+ /* FXSR disabled? */
+ if (disable_x86_fxsr) {
+ clear_bit(X86_FEATURE_FXSR, c->x86_capability);
+ clear_bit(X86_FEATURE_XMM, c->x86_capability);
+ }
+
+ /* SEP disabled? */
+ if (disable_x86_sep)
+ clear_bit(X86_FEATURE_SEP, c->x86_capability);
+
+ if (disable_pse)
+ clear_bit(X86_FEATURE_PSE, c->x86_capability);
+
/* If the model name is still unset, do table lookup. */
if ( !c->x86_model_id[0] ) {
char *p;
@@ -487,6 +482,13 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
c->x86, c->x86_model);
}
+ /* Now the feature flags better reflect actual CPU features! */
+
+ printk(KERN_DEBUG "CPU: After all inits, caps:");
+ for (i = 0; i < NCAPINTS; i++)
+ printk(" %08lx", c->x86_capability[i]);
+ printk("\n");
+
/*
* On SMP, boot_cpu_data holds the common feature set between
* all CPUs; so make sure that we indicate which features are
@@ -499,14 +501,8 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
}
- /* Clear all flags overriden by options */
- for (i = 0; i < NCAPINTS; i++)
- c->x86_capability[i] ^= cleared_cpu_caps[i];
-
/* Init Machine Check Exception if available. */
mcheck_init(c);
-
- select_idle_routine(c);
}
void __init identify_boot_cpu(void)
@@ -514,6 +510,7 @@ void __init identify_boot_cpu(void)
identify_cpu(&boot_cpu_data);
sysenter_setup();
enable_sep_cpu();
+ mtrr_bp_init();
}
void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
@@ -570,13 +567,6 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
}
#endif
-static __init int setup_noclflush(char *arg)
-{
- setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
- return 1;
-}
-__setup("noclflush", setup_noclflush);
-
void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
{
char *vendor = NULL;
@@ -600,17 +590,6 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
printk("\n");
}
-static __init int setup_disablecpuid(char *arg)
-{
- int bit;
- if (get_option(&arg, &bit) && bit < NCAPINTS*32)
- setup_clear_cpu_cap(bit);
- else
- return 0;
- return 1;
-}
-__setup("clearcpuid=", setup_disablecpuid);
-
cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
/* This is hacky. :)
@@ -641,13 +620,21 @@ void __init early_cpu_init(void)
nexgen_init_cpu();
umc_init_cpu();
early_cpu_detect();
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ /* pse is not compatible with on-the-fly unmapping,
+ * disable it even if the cpus claim to support it.
+ */
+ clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability);
+ disable_pse = 1;
+#endif
}
/* Make sure %fs is initialized properly in idle threads */
struct pt_regs * __devinit idle_regs(struct pt_regs *regs)
{
memset(regs, 0, sizeof(struct pt_regs));
- regs->fs = __KERNEL_PERCPU;
+ regs->xfs = __KERNEL_PERCPU;
return regs;
}
@@ -655,7 +642,7 @@ struct pt_regs * __devinit idle_regs(struct pt_regs *regs)
* it's on the real one. */
void switch_to_new_gdt(void)
{
- struct desc_ptr gdt_descr;
+ struct Xgt_desc_struct gdt_descr;
gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
gdt_descr.size = GDT_SIZE - 1;
@@ -685,6 +672,12 @@ void __cpuinit cpu_init(void)
if (cpu_has_vme || cpu_has_tsc || cpu_has_de)
clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+ if (tsc_disable && cpu_has_tsc) {
+ printk(KERN_NOTICE "Disabling TSC...\n");
+ /**** FIX-HPA: DOES THIS REALLY BELONG HERE? ****/
+ clear_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability);
+ set_in_cr4(X86_CR4_TSD);
+ }
load_idt(&idt_descr);
switch_to_new_gdt();
@@ -698,7 +691,7 @@ void __cpuinit cpu_init(void)
BUG();
enter_lazy_tlb(&init_mm, curr);
- load_sp0(t, thread);
+ load_esp0(t, thread);
set_tss_desc(cpu,t);
load_TR_desc();
load_LDT(&init_mm.context);
diff --git a/trunk/arch/x86/kernel/cpu/cpu.h b/trunk/arch/x86/kernel/cpu/cpu.h
index ad6527a5beb1..2f6432cef6ff 100644
--- a/trunk/arch/x86/kernel/cpu/cpu.h
+++ b/trunk/arch/x86/kernel/cpu/cpu.h
@@ -24,6 +24,5 @@ extern struct cpu_dev * cpu_devs [X86_VENDOR_NUM];
extern int get_model_name(struct cpuinfo_x86 *c);
extern void display_cacheinfo(struct cpuinfo_x86 *c);
-extern void early_init_intel(struct cpuinfo_x86 *c);
-extern void early_init_amd(struct cpuinfo_x86 *c);
+extern void early_intel_workaround(struct cpuinfo_x86 *c);
diff --git a/trunk/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/trunk/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index a962dcb9c408..fea0af0476b9 100644
--- a/trunk/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/trunk/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -67,8 +67,7 @@ struct acpi_cpufreq_data {
unsigned int cpu_feature;
};
-static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
-
+static struct acpi_cpufreq_data *drv_data[NR_CPUS];
/* acpi_perf_data is a pointer to percpu data. */
static struct acpi_processor_performance *acpi_perf_data;
@@ -219,14 +218,14 @@ static u32 get_cur_val(cpumask_t mask)
if (unlikely(cpus_empty(mask)))
return 0;
- switch (per_cpu(drv_data, first_cpu(mask))->cpu_feature) {
+ switch (drv_data[first_cpu(mask)]->cpu_feature) {
case SYSTEM_INTEL_MSR_CAPABLE:
cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
break;
case SYSTEM_IO_CAPABLE:
cmd.type = SYSTEM_IO_CAPABLE;
- perf = per_cpu(drv_data, first_cpu(mask))->acpi_data;
+ perf = drv_data[first_cpu(mask)]->acpi_data;
cmd.addr.io.port = perf->control_register.address;
cmd.addr.io.bit_width = perf->control_register.bit_width;
break;
@@ -326,7 +325,7 @@ static unsigned int get_measured_perf(unsigned int cpu)
#endif
- retval = per_cpu(drv_data, cpu)->max_freq * perf_percent / 100;
+ retval = drv_data[cpu]->max_freq * perf_percent / 100;
put_cpu();
set_cpus_allowed(current, saved_mask);
@@ -337,7 +336,7 @@ static unsigned int get_measured_perf(unsigned int cpu)
static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
+ struct acpi_cpufreq_data *data = drv_data[cpu];
unsigned int freq;
dprintk("get_cur_freq_on_cpu (%d)\n", cpu);
@@ -371,7 +370,7 @@ static unsigned int check_freqs(cpumask_t mask, unsigned int freq,
static int acpi_cpufreq_target(struct cpufreq_policy *policy,
unsigned int target_freq, unsigned int relation)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = drv_data[policy->cpu];
struct acpi_processor_performance *perf;
struct cpufreq_freqs freqs;
cpumask_t online_policy_cpus;
@@ -467,7 +466,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
static int acpi_cpufreq_verify(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = drv_data[policy->cpu];
dprintk("acpi_cpufreq_verify\n");
@@ -571,7 +570,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
return -ENOMEM;
data->acpi_data = percpu_ptr(acpi_perf_data, cpu);
- per_cpu(drv_data, cpu) = data;
+ drv_data[cpu] = data;
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
@@ -715,20 +714,20 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
acpi_processor_unregister_performance(perf, cpu);
err_free:
kfree(data);
- per_cpu(drv_data, cpu) = NULL;
+ drv_data[cpu] = NULL;
return result;
}
static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = drv_data[policy->cpu];
dprintk("acpi_cpufreq_cpu_exit\n");
if (data) {
cpufreq_frequency_table_put_attr(policy->cpu);
- per_cpu(drv_data, policy->cpu) = NULL;
+ drv_data[policy->cpu] = NULL;
acpi_processor_unregister_performance(data->acpi_data,
policy->cpu);
kfree(data);
@@ -739,7 +738,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = drv_data[policy->cpu];
dprintk("acpi_cpufreq_resume\n");
diff --git a/trunk/arch/x86/kernel/cpu/cpufreq/longhaul.c b/trunk/arch/x86/kernel/cpu/cpufreq/longhaul.c
index 06fcce516d51..749d00cb2ebd 100644
--- a/trunk/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/trunk/arch/x86/kernel/cpu/cpufreq/longhaul.c
@@ -694,7 +694,7 @@ static acpi_status longhaul_walk_callback(acpi_handle obj_handle,
if ( acpi_bus_get_device(obj_handle, &d) ) {
return 0;
}
- *return_value = acpi_driver_data(d);
+ *return_value = (void *)acpi_driver_data(d);
return 1;
}
diff --git a/trunk/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/trunk/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index a0522735dd9d..99e1ef9939be 100644
--- a/trunk/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/trunk/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -52,7 +52,7 @@
/* serialize freq changes */
static DEFINE_MUTEX(fidvid_mutex);
-static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
+static struct powernow_k8_data *powernow_data[NR_CPUS];
static int cpu_family = CPU_OPTERON;
@@ -1018,7 +1018,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i
static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation)
{
cpumask_t oldmask = CPU_MASK_ALL;
- struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
+ struct powernow_k8_data *data = powernow_data[pol->cpu];
u32 checkfid;
u32 checkvid;
unsigned int newstate;
@@ -1094,7 +1094,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
/* Driver entry point to verify the policy and range of frequencies */
static int powernowk8_verify(struct cpufreq_policy *pol)
{
- struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
+ struct powernow_k8_data *data = powernow_data[pol->cpu];
if (!data)
return -EINVAL;
@@ -1202,7 +1202,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
dprintk("cpu_init done, current fid 0x%x, vid 0x%x\n",
data->currfid, data->currvid);
- per_cpu(powernow_data, pol->cpu) = data;
+ powernow_data[pol->cpu] = data;
return 0;
@@ -1216,7 +1216,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
static int __devexit powernowk8_cpu_exit (struct cpufreq_policy *pol)
{
- struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
+ struct powernow_k8_data *data = powernow_data[pol->cpu];
if (!data)
return -EINVAL;
@@ -1237,7 +1237,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
cpumask_t oldmask = current->cpus_allowed;
unsigned int khz = 0;
- data = per_cpu(powernow_data, first_cpu(per_cpu(cpu_core_map, cpu)));
+ data = powernow_data[first_cpu(per_cpu(cpu_core_map, cpu))];
if (!data)
return -EINVAL;
diff --git a/trunk/arch/x86/kernel/cpu/cyrix.c b/trunk/arch/x86/kernel/cpu/cyrix.c
index 404a6a2d4016..88d66fb8411d 100644
--- a/trunk/arch/x86/kernel/cpu/cyrix.c
+++ b/trunk/arch/x86/kernel/cpu/cyrix.c
@@ -5,7 +5,6 @@
#include
#include
#include
-#include
#include
#include
#include
@@ -127,12 +126,15 @@ static void __cpuinit set_cx86_reorder(void)
static void __cpuinit set_cx86_memwb(void)
{
+ u32 cr0;
+
printk(KERN_INFO "Enable Memory-Write-back mode on Cyrix/NSC processor.\n");
/* CCR2 bit 2: unlock NW bit */
setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04);
/* set 'Not Write-through' */
- write_cr0(read_cr0() | X86_CR0_NW);
+ cr0 = 0x20000000;
+ write_cr0(read_cr0() | cr0);
/* CCR2 bit 2: lock NW bit and set WT1 */
setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14 );
}
diff --git a/trunk/arch/x86/kernel/cpu/intel.c b/trunk/arch/x86/kernel/cpu/intel.c
index d1c372b018db..cc8c501b9f39 100644
--- a/trunk/arch/x86/kernel/cpu/intel.c
+++ b/trunk/arch/x86/kernel/cpu/intel.c
@@ -11,8 +11,6 @@
#include
#include
#include
-#include
-#include
#include "cpu.h"
@@ -29,14 +27,13 @@
struct movsl_mask movsl_mask __read_mostly;
#endif
-void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
+void __cpuinit early_intel_workaround(struct cpuinfo_x86 *c)
{
+ if (c->x86_vendor != X86_VENDOR_INTEL)
+ return;
/* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
if (c->x86 == 15 && c->x86_cache_alignment == 64)
c->x86_cache_alignment = 128;
- if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
- (c->x86 == 0x6 && c->x86_model >= 0x0e))
- set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
}
/*
@@ -116,8 +113,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
unsigned int l2 = 0;
char *p = NULL;
- early_init_intel(c);
-
#ifdef CONFIG_X86_F00F_BUG
/*
* All current models of Pentium and Pentium with MMX technology CPUs
@@ -137,6 +132,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
}
#endif
+ select_idle_routine(c);
l2 = init_intel_cacheinfo(c);
if (c->cpuid_level > 9 ) {
unsigned eax = cpuid_eax(10);
@@ -205,13 +201,16 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
}
#endif
- if (cpu_has_xmm2)
- set_bit(X86_FEATURE_LFENCE_RDTSC, c->x86_capability);
if (c->x86 == 15) {
set_bit(X86_FEATURE_P4, c->x86_capability);
+ set_bit(X86_FEATURE_SYNC_RDTSC, c->x86_capability);
}
if (c->x86 == 6)
set_bit(X86_FEATURE_P3, c->x86_capability);
+ if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
+ (c->x86 == 0x6 && c->x86_model >= 0x0e))
+ set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
+
if (cpu_has_ds) {
unsigned int l1;
rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
@@ -220,9 +219,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
if (!(l1 & (1<<12)))
set_bit(X86_FEATURE_PEBS, c->x86_capability);
}
-
- if (cpu_has_bts)
- ds_init_intel(c);
}
static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 * c, unsigned int size)
@@ -346,22 +342,5 @@ unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
EXPORT_SYMBOL(cmpxchg_386_u32);
#endif
-#ifndef CONFIG_X86_CMPXCHG64
-unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new)
-{
- u64 prev;
- unsigned long flags;
-
- /* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */
- local_irq_save(flags);
- prev = *(u64 *)ptr;
- if (prev == old)
- *(u64 *)ptr = new;
- local_irq_restore(flags);
- return prev;
-}
-EXPORT_SYMBOL(cmpxchg_486_u64);
-#endif
-
// arch_initcall(intel_cpu_init);
diff --git a/trunk/arch/x86/kernel/cpu/mcheck/k7.c b/trunk/arch/x86/kernel/cpu/mcheck/k7.c
index e633c9c2b764..eef63e3630c2 100644
--- a/trunk/arch/x86/kernel/cpu/mcheck/k7.c
+++ b/trunk/arch/x86/kernel/cpu/mcheck/k7.c
@@ -16,7 +16,7 @@
#include "mce.h"
/* Machine Check Handler For AMD Athlon/Duron */
-static void k7_machine_check(struct pt_regs * regs, long error_code)
+static fastcall void k7_machine_check(struct pt_regs * regs, long error_code)
{
int recover=1;
u32 alow, ahigh, high, low;
@@ -27,32 +27,29 @@ static void k7_machine_check(struct pt_regs * regs, long error_code)
if (mcgstl & (1<<0)) /* Recoverable ? */
recover=0;
- printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
+ printk (KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
smp_processor_id(), mcgsth, mcgstl);
- for (i = 1; i < nr_mce_banks; i++) {
- rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
+ for (i=1; i= MCE_LOG_LEN) {
- set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags);
+ set_bit(MCE_OVERFLOW, &mcelog.flags);
return;
}
/* Old left over entry. Skip. */
@@ -110,12 +110,12 @@ static void print_mce(struct mce *m)
KERN_EMERG
"CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
m->cpu, m->mcgstatus, m->bank, m->status);
- if (m->ip) {
+ if (m->rip) {
printk(KERN_EMERG "RIP%s %02x:<%016Lx> ",
!(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
- m->cs, m->ip);
+ m->cs, m->rip);
if (m->cs == __KERNEL_CS)
- print_symbol("{%s}", m->ip);
+ print_symbol("{%s}", m->rip);
printk("\n");
}
printk(KERN_EMERG "TSC %Lx ", m->tsc);
@@ -156,16 +156,16 @@ static int mce_available(struct cpuinfo_x86 *c)
static inline void mce_get_rip(struct mce *m, struct pt_regs *regs)
{
if (regs && (m->mcgstatus & MCG_STATUS_RIPV)) {
- m->ip = regs->ip;
+ m->rip = regs->rip;
m->cs = regs->cs;
} else {
- m->ip = 0;
+ m->rip = 0;
m->cs = 0;
}
if (rip_msr) {
/* Assume the RIP in the MSR is exact. Is this true? */
m->mcgstatus |= MCG_STATUS_EIPV;
- rdmsrl(rip_msr, m->ip);
+ rdmsrl(rip_msr, m->rip);
m->cs = 0;
}
}
@@ -192,10 +192,10 @@ void do_machine_check(struct pt_regs * regs, long error_code)
atomic_inc(&mce_entry);
- if ((regs
- && notify_die(DIE_NMI, "machine check", regs, error_code,
- 18, SIGKILL) == NOTIFY_STOP)
- || !banks)
+ if (regs)
+ notify_die(DIE_NMI, "machine check", regs, error_code, 18,
+ SIGKILL);
+ if (!banks)
goto out2;
memset(&m, 0, sizeof(struct mce));
@@ -288,7 +288,7 @@ void do_machine_check(struct pt_regs * regs, long error_code)
* instruction which caused the MCE.
*/
if (m.mcgstatus & MCG_STATUS_EIPV)
- user_space = panicm.ip && (panicm.cs & 3);
+ user_space = panicm.rip && (panicm.cs & 3);
/*
* If we know that the error was in user space, send a
@@ -564,7 +564,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
loff_t *off)
{
unsigned long *cpu_tsc;
- static DEFINE_MUTEX(mce_read_mutex);
+ static DECLARE_MUTEX(mce_read_sem);
unsigned next;
char __user *buf = ubuf;
int i, err;
@@ -573,12 +573,12 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
if (!cpu_tsc)
return -ENOMEM;
- mutex_lock(&mce_read_mutex);
+ down(&mce_read_sem);
next = rcu_dereference(mcelog.next);
/* Only supports full reads right now */
if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
- mutex_unlock(&mce_read_mutex);
+ up(&mce_read_sem);
kfree(cpu_tsc);
return -EINVAL;
}
@@ -621,7 +621,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
memset(&mcelog.entry[i], 0, sizeof(struct mce));
}
}
- mutex_unlock(&mce_read_mutex);
+ up(&mce_read_sem);
kfree(cpu_tsc);
return err ? -EFAULT : buf - ubuf;
}
@@ -634,7 +634,8 @@ static unsigned int mce_poll(struct file *file, poll_table *wait)
return 0;
}
-static long mce_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
+static int mce_ioctl(struct inode *i, struct file *f,unsigned int cmd,
+ unsigned long arg)
{
int __user *p = (int __user *)arg;
@@ -663,7 +664,7 @@ static const struct file_operations mce_chrdev_ops = {
.release = mce_release,
.read = mce_read,
.poll = mce_poll,
- .unlocked_ioctl = mce_ioctl,
+ .ioctl = mce_ioctl,
};
static struct miscdevice mce_log_device = {
@@ -854,8 +855,8 @@ static void mce_remove_device(unsigned int cpu)
}
/* Get notified when a cpu comes on/off. Be hotplug friendly. */
-static int __cpuinit mce_cpu_callback(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+static int
+mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
unsigned int cpu = (unsigned long)hcpu;
@@ -872,7 +873,7 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb,
return NOTIFY_OK;
}
-static struct notifier_block mce_cpu_notifier __cpuinitdata = {
+static struct notifier_block mce_cpu_notifier = {
.notifier_call = mce_cpu_callback,
};
diff --git a/trunk/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/trunk/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 32671da8184e..753588755fee 100644
--- a/trunk/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/trunk/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -118,7 +118,6 @@ void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
{
unsigned int bank, block;
unsigned int cpu = smp_processor_id();
- u8 lvt_off;
u32 low = 0, high = 0, address = 0;
for (bank = 0; bank < NR_BANKS; ++bank) {
@@ -154,13 +153,14 @@ void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
if (shared_bank[bank] && c->cpu_core_id)
break;
#endif
- lvt_off = setup_APIC_eilvt_mce(THRESHOLD_APIC_VECTOR,
- APIC_EILVT_MSG_FIX, 0);
-
high &= ~MASK_LVTOFF_HI;
- high |= lvt_off << 20;
+ high |= K8_APIC_EXT_LVT_ENTRY_THRESHOLD << 20;
wrmsr(address, low, high);
+ setup_APIC_extended_lvt(K8_APIC_EXT_LVT_ENTRY_THRESHOLD,
+ THRESHOLD_APIC_VECTOR,
+ K8_APIC_EXT_INT_MSG_FIX, 0);
+
threshold_defaults.address = address;
threshold_restart_bank(&threshold_defaults, 0, 0);
}
@@ -450,8 +450,7 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu,
if (err)
goto out_free;
- if (b)
- kobject_uevent(&b->kobj, KOBJ_ADD);
+ kobject_uevent(&b->kobj, KOBJ_ADD);
return err;
@@ -555,7 +554,7 @@ static __cpuinit int threshold_create_device(unsigned int cpu)
int err = 0;
for (bank = 0; bank < NR_BANKS; ++bank) {
- if (!(per_cpu(bank_map, cpu) & (1 << bank)))
+ if (!(per_cpu(bank_map, cpu) & 1 << bank))
continue;
err = threshold_create_bank(cpu, bank);
if (err)
@@ -638,14 +637,14 @@ static void threshold_remove_device(unsigned int cpu)
unsigned int bank;
for (bank = 0; bank < NR_BANKS; ++bank) {
- if (!(per_cpu(bank_map, cpu) & (1 << bank)))
+ if (!(per_cpu(bank_map, cpu) & 1 << bank))
continue;
threshold_remove_bank(cpu, bank);
}
}
/* get notified when a cpu comes on/off */
-static int __cpuinit threshold_cpu_callback(struct notifier_block *nfb,
+static int threshold_cpu_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
/* cpu was unsigned int to begin with */
@@ -670,7 +669,7 @@ static int __cpuinit threshold_cpu_callback(struct notifier_block *nfb,
return NOTIFY_OK;
}
-static struct notifier_block threshold_cpu_notifier __cpuinitdata = {
+static struct notifier_block threshold_cpu_notifier = {
.notifier_call = threshold_cpu_callback,
};
diff --git a/trunk/arch/x86/kernel/cpu/mcheck/p4.c b/trunk/arch/x86/kernel/cpu/mcheck/p4.c
index cb03345554a5..be4dabfee1f5 100644
--- a/trunk/arch/x86/kernel/cpu/mcheck/p4.c
+++ b/trunk/arch/x86/kernel/cpu/mcheck/p4.c
@@ -57,7 +57,7 @@ static void intel_thermal_interrupt(struct pt_regs *regs)
/* Thermal interrupt handler for this CPU setup */
static void (*vendor_thermal_interrupt)(struct pt_regs *regs) = unexpected_thermal_interrupt;
-void smp_thermal_interrupt(struct pt_regs *regs)
+fastcall void smp_thermal_interrupt(struct pt_regs *regs)
{
irq_enter();
vendor_thermal_interrupt(regs);
@@ -141,7 +141,7 @@ static inline void intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
rdmsr (MSR_IA32_MCG_EIP, r->eip, h);
}
-static void intel_machine_check(struct pt_regs * regs, long error_code)
+static fastcall void intel_machine_check(struct pt_regs * regs, long error_code)
{
int recover=1;
u32 alow, ahigh, high, low;
@@ -152,41 +152,38 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
if (mcgstl & (1<<0)) /* Recoverable ? */
recover=0;
- printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
+ printk (KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
smp_processor_id(), mcgsth, mcgstl);
if (mce_num_extended_msrs > 0) {
struct intel_mce_extended_msrs dbg;
intel_get_extended_msrs(&dbg);
- printk(KERN_DEBUG "CPU %d: EIP: %08x EFLAGS: %08x\n"
- "\teax: %08x ebx: %08x ecx: %08x edx: %08x\n"
- "\tesi: %08x edi: %08x ebp: %08x esp: %08x\n",
- smp_processor_id(), dbg.eip, dbg.eflags,
- dbg.eax, dbg.ebx, dbg.ecx, dbg.edx,
+ printk (KERN_DEBUG "CPU %d: EIP: %08x EFLAGS: %08x\n",
+ smp_processor_id(), dbg.eip, dbg.eflags);
+ printk (KERN_DEBUG "\teax: %08x ebx: %08x ecx: %08x edx: %08x\n",
+ dbg.eax, dbg.ebx, dbg.ecx, dbg.edx);
+ printk (KERN_DEBUG "\tesi: %08x edi: %08x ebp: %08x esp: %08x\n",
dbg.esi, dbg.edi, dbg.ebp, dbg.esp);
}
- for (i = 0; i < nr_mce_banks; i++) {
- rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
+ for (i=0; i The base address of the region.
The size of the region. If this is 0 the region is disabled.
The type of the region.
+ If TRUE, do the change safely. If FALSE, safety measures should
+ be done externally.
[RETURNS] Nothing.
*/
{
diff --git a/trunk/arch/x86/kernel/cpu/mtrr/cyrix.c b/trunk/arch/x86/kernel/cpu/mtrr/cyrix.c
index 8e139c70f888..9964be3de2b7 100644
--- a/trunk/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/trunk/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -4,7 +4,6 @@
#include
#include
#include
-#include
#include "mtrr.h"
int arr3_protected;
@@ -143,7 +142,7 @@ static void prepare_set(void)
/* Disable and flush caches. Note that wbinvd flushes the TLBs as
a side-effect */
- cr0 = read_cr0() | X86_CR0_CD;
+ cr0 = read_cr0() | 0x40000000;
wbinvd();
write_cr0(cr0);
wbinvd();
diff --git a/trunk/arch/x86/kernel/cpu/mtrr/generic.c b/trunk/arch/x86/kernel/cpu/mtrr/generic.c
index 103d61a59b19..992f08dfbb6c 100644
--- a/trunk/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/trunk/arch/x86/kernel/cpu/mtrr/generic.c
@@ -9,12 +9,11 @@
#include
#include
#include
-#include
#include
#include "mtrr.h"
struct mtrr_state {
- struct mtrr_var_range var_ranges[MAX_VAR_RANGES];
+ struct mtrr_var_range *var_ranges;
mtrr_type fixed_ranges[NUM_FIXED_RANGES];
unsigned char enabled;
unsigned char have_fixed;
@@ -86,6 +85,12 @@ void __init get_mtrr_state(void)
struct mtrr_var_range *vrs;
unsigned lo, dummy;
+ if (!mtrr_state.var_ranges) {
+ mtrr_state.var_ranges = kmalloc(num_var_ranges * sizeof (struct mtrr_var_range),
+ GFP_KERNEL);
+ if (!mtrr_state.var_ranges)
+ return;
+ }
vrs = mtrr_state.var_ranges;
rdmsr(MTRRcap_MSR, lo, dummy);
@@ -183,7 +188,7 @@ static inline void k8_enable_fixed_iorrs(void)
* \param changed pointer which indicates whether the MTRR needed to be changed
* \param msrwords pointer to the MSR values which the MSR should have
*/
-static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords)
+static void set_fixed_range(int msr, int * changed, unsigned int * msrwords)
{
unsigned lo, hi;
@@ -195,7 +200,7 @@ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords)
((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK))
k8_enable_fixed_iorrs();
mtrr_wrmsr(msr, msrwords[0], msrwords[1]);
- *changed = true;
+ *changed = TRUE;
}
}
@@ -255,7 +260,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
static int set_fixed_ranges(mtrr_type * frs)
{
unsigned long long *saved = (unsigned long long *) frs;
- bool changed = false;
+ int changed = FALSE;
int block=-1, range;
while (fixed_range_blocks[++block].ranges)
@@ -268,17 +273,17 @@ static int set_fixed_ranges(mtrr_type * frs)
/* Set the MSR pair relating to a var range. Returns TRUE if
changes are made */
-static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
+static int set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
{
unsigned int lo, hi;
- bool changed = false;
+ int changed = FALSE;
rdmsr(MTRRphysBase_MSR(index), lo, hi);
if ((vr->base_lo & 0xfffff0ffUL) != (lo & 0xfffff0ffUL)
|| (vr->base_hi & (size_and_mask >> (32 - PAGE_SHIFT))) !=
(hi & (size_and_mask >> (32 - PAGE_SHIFT)))) {
mtrr_wrmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi);
- changed = true;
+ changed = TRUE;
}
rdmsr(MTRRphysMask_MSR(index), lo, hi);
@@ -287,7 +292,7 @@ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
|| (vr->mask_hi & (size_and_mask >> (32 - PAGE_SHIFT))) !=
(hi & (size_and_mask >> (32 - PAGE_SHIFT)))) {
mtrr_wrmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi);
- changed = true;
+ changed = TRUE;
}
return changed;
}
@@ -345,7 +350,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
spin_lock(&set_atomicity_lock);
/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
- cr0 = read_cr0() | X86_CR0_CD;
+ cr0 = read_cr0() | 0x40000000; /* set CD flag */
write_cr0(cr0);
wbinvd();
@@ -412,6 +417,8 @@ static void generic_set_mtrr(unsigned int reg, unsigned long base,
The base address of the region.
The size of the region. If this is 0 the region is disabled.
The type of the region.
+ If TRUE, do the change safely. If FALSE, safety measures should
+ be done externally.
[RETURNS] Nothing.
*/
{
diff --git a/trunk/arch/x86/kernel/cpu/mtrr/if.c b/trunk/arch/x86/kernel/cpu/mtrr/if.c
index 91e150acb46c..c7d8f1756745 100644
--- a/trunk/arch/x86/kernel/cpu/mtrr/if.c
+++ b/trunk/arch/x86/kernel/cpu/mtrr/if.c
@@ -11,6 +11,10 @@
#include
#include "mtrr.h"
+/* RED-PEN: this is accessed without any locking */
+extern unsigned int *usage_table;
+
+
#define FILE_FCOUNT(f) (((struct seq_file *)((f)->private_data))->private)
static const char *const mtrr_strings[MTRR_NUM_TYPES] =
@@ -33,7 +37,7 @@ const char *mtrr_attrib_to_str(int x)
static int
mtrr_file_add(unsigned long base, unsigned long size,
- unsigned int type, bool increment, struct file *file, int page)
+ unsigned int type, char increment, struct file *file, int page)
{
int reg, max;
unsigned int *fcount = FILE_FCOUNT(file);
@@ -51,7 +55,7 @@ mtrr_file_add(unsigned long base, unsigned long size,
base >>= PAGE_SHIFT;
size >>= PAGE_SHIFT;
}
- reg = mtrr_add_page(base, size, type, true);
+ reg = mtrr_add_page(base, size, type, 1);
if (reg >= 0)
++fcount[reg];
return reg;
@@ -137,7 +141,7 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
size >>= PAGE_SHIFT;
err =
mtrr_add_page((unsigned long) base, (unsigned long) size, i,
- true);
+ 1);
if (err < 0)
return err;
return len;
@@ -213,7 +217,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
err =
- mtrr_file_add(sentry.base, sentry.size, sentry.type, true,
+ mtrr_file_add(sentry.base, sentry.size, sentry.type, 1,
file, 0);
break;
case MTRRIOC_SET_ENTRY:
@@ -222,7 +226,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
#endif
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- err = mtrr_add(sentry.base, sentry.size, sentry.type, false);
+ err = mtrr_add(sentry.base, sentry.size, sentry.type, 0);
break;
case MTRRIOC_DEL_ENTRY:
#ifdef CONFIG_COMPAT
@@ -266,7 +270,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
err =
- mtrr_file_add(sentry.base, sentry.size, sentry.type, true,
+ mtrr_file_add(sentry.base, sentry.size, sentry.type, 1,
file, 1);
break;
case MTRRIOC_SET_PAGE_ENTRY:
@@ -275,8 +279,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
#endif
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- err =
- mtrr_add_page(sentry.base, sentry.size, sentry.type, false);
+ err = mtrr_add_page(sentry.base, sentry.size, sentry.type, 0);
break;
case MTRRIOC_DEL_PAGE_ENTRY:
#ifdef CONFIG_COMPAT
@@ -393,7 +396,7 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset)
for (i = 0; i < max; i++) {
mtrr_if->get(i, &base, &size, &type);
if (size == 0)
- mtrr_usage_table[i] = 0;
+ usage_table[i] = 0;
else {
if (size < (0x100000 >> PAGE_SHIFT)) {
/* less than 1MB */
@@ -407,7 +410,7 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset)
len += seq_printf(seq,
"reg%02i: base=0x%05lx000 (%4luMB), size=%4lu%cB: %s, count=%d\n",
i, base, base >> (20 - PAGE_SHIFT), size, factor,
- mtrr_attrib_to_str(type), mtrr_usage_table[i]);
+ mtrr_attrib_to_str(type), usage_table[i]);
}
}
return 0;
diff --git a/trunk/arch/x86/kernel/cpu/mtrr/main.c b/trunk/arch/x86/kernel/cpu/mtrr/main.c
index 715919582657..beb45c9c0835 100644
--- a/trunk/arch/x86/kernel/cpu/mtrr/main.c
+++ b/trunk/arch/x86/kernel/cpu/mtrr/main.c
@@ -38,8 +38,8 @@
#include
#include
-#include
#include
+
#include